AmanPriyanshu/gpt-oss-8.4b-specialized-law-pruned-moe-only-11-experts

Law GPT-OSS Model (11 Experts)

Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/

👥 Follow the Authors

Aman Priyanshu

Supriti Vijay

Introduction

This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 11 experts per layer based on activation patterns from the AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset. We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for law tasks.

⚠️ Experimental Model: This is an experimental pruned model that may not work well - check the examples below to see if the outputs meet your needs before use.

This pruning approach reduces the model size while attempting to preserve performance on the target domain.

Model Architecture & Statistics

Metric	Value
Base Model	openai/gpt-oss-20b
Architecture	Mixture-of-Experts Transformer
Total Parameters	~8.4B (pruned from 21B)
Original Experts per Layer	32
Pruned Experts per Layer	11
Layers	24
Top-k Routing	4
Context Length	128K tokens
Attention Heads	64 (Query), 8 (Key-Value)
Residual Dimension	2880
Attention Pattern	Alternating dense & sliding window (128 tokens)
Positional Encoding	RoPE (Rotary Position Embedding)
Normalization	RMSNorm
Precision	BF16
License	Apache 2.0
Specialization	Law

Pruning Methodology

What is Expert Pruning?

Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:

1. Analyzing Usage Patterns: Tracking which experts activate most frequently for specific tasks
2. Removing Underutilized Experts: Discarding experts with low activation rates for the target domain
3. Preserving Router Functionality: Maintaining the routing mechanism with fewer available experts

Our Approach

• Data-Driven Selection: Used activation patterns from law evaluation tasks
• Systematic Reduction: Reduced from 32 to 11 experts per layer
• No Retraining: Direct removal without additional training steps

Performance & Applications

Pruning Benefits

• Smaller Memory Footprint: 34.4% of original expert parameters
• Reduced Computational Load: Fewer routing decisions during inference
• Focused Capabilities: Retains experts relevant to law tasks

Use Cases

• Speculative Decoding: Draft model for full GPT-OSS-20B
• Resource-Constrained Deployment: Edge devices, mobile applications
• Research: Study expert specialization in MoE models
• Fine-tuning: Smaller base model for domain adaptation

Note: Performance may vary depending on how well the pruned experts match your specific use case.

Motivation & Expert Selection

This legal domain model employs experts that demonstrated expertise during law-related tasks from MMLU legal subjects. These experts excel at legal reasoning, jurisprudence, and understanding of legal frameworks and procedures.

The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:

• GPQA: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
• MMLU/MMLU-Pro: Comprehensive knowledge across 57+ subjects including science, medicine, law
• SORRY-Bench: Safety evaluation across harmful content categories
• Tulu3: Persona-driven instruction following with verifiable constraints
• Polyglot-or-Not: Multilingual factual completion tasks

By identifying experts that consistently activated for law tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 11 experts per layer.

Dataset & Analysis Foundation

This model is based on analysis from the GPT-OSS-20B MoE Expert Activations dataset available at: 🔗 https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations

The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.

Pruning Methodology

Our approach involves:

1. Activation Analysis: Comprehensive evaluation of expert usage patterns across domain-specific tasks
2. Expert Ranking: Identification of the most frequently activated experts for target domains
3. Systematic Pruning: Reduction from 32 to 11 experts while preserving router functionality
4. Quality Validation: Testing to ensure maintained performance on target tasks

This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.

Usage

CPU Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
    "AmanPriyanshu/gpt-oss-8.4b-specialized-law-pruned-moe-only-11-experts", 
    torch_dtype=torch.bfloat16, 
    device_map="cpu", 
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-law-pruned-moe-only-11-experts")

# Generate with the model
messages = [
    {"role": "user", "content": "What is the difference between civil and criminal law?"}
]

inputs = tokenizer.apply_chat_template(
    messages, 
    add_generation_prompt=True, 
    return_tensors="pt", 
    return_dict=True,
    reasoning_effort="medium"
)

# Ensure inputs are on the same device as model
inputs = {k: v.to(model.device) for k, v in inputs.items()}

outputs = model.generate(
    **inputs, 
    max_new_tokens=512,
    do_sample=True,
    temperature=0.1,
    top_p=0.9,
    pad_token_id=tokenizer.eos_token_id,
    eos_token_id=tokenizer.eos_token_id
)

# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)

Apple Silicon (MPS) Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Check MPS availability and load model
device = "mps" if torch.backends.mps.is_available() else "cpu"

model = AutoModelForCausalLM.from_pretrained(
    "AmanPriyanshu/gpt-oss-8.4b-specialized-law-pruned-moe-only-11-experts", 
    torch_dtype=torch.float16,  # Better MPS compatibility
    device_map=device, 
    trust_remote_code=True,
    low_cpu_mem_usage=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-law-pruned-moe-only-11-experts")

# Generate with the model
messages = [
    {"role": "user", "content": "What is the difference between civil and criminal law?"}
]

inputs = tokenizer.apply_chat_template(
    messages, 
    add_generation_prompt=True, 
    return_tensors="pt", 
    return_dict=True,
    reasoning_effort="medium"
)

# Move inputs to model device
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}

# Use torch.no_grad for MPS stability
with torch.no_grad():
    outputs = model.generate(
        **inputs, 
        max_new_tokens=512,
        do_sample=True,
        temperature=0.1,
        top_p=0.9,
        pad_token_id=tokenizer.eos_token_id,
        eos_token_id=tokenizer.eos_token_id,
        use_cache=True
    )

# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)

GPU Inference

For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:

device_map="auto"  # Will automatically use GPU if available
torch_dtype=torch.bfloat16  # or torch.float16

Model Examples

The following examples demonstrate the model's performance on law tasks:

Example 1

Question: What is the difference between civil and criminal law?

Response:

<|channel|>analysis<|message|>Need to explain difference: civil law is disputes between private parties, remedies like damages, injunctions; criminal law is offenses against state, punishments like fines, imprisonment, etc. Also mention jurisdiction, burden of proof, standard of proof, etc.<|end|><|start|>assistant<|channel|>final<|message|>**Civil law vs. criminal law**

| Feature | Civil law | Criminal law |
|---|---|---|
| **Purpose** | Resolve disputes between private parties (e.g., contracts, torts, property, family matters). | Protect society and the state by puning conduct that is deemed harmful or dangerous. |
| **Parties** | Plaintiff (private individual or entity) vs. defendant (private individual or entity). | State (or government) vs. defendant (private individual or entity). |
| **Rem remedy** | Monetary damages, injunctions, specific performance, or restitution. | Penative sanctions: fines, community service, probation, imprisonment, or death in extreme cases. |
| **Bur burden of proof** | “Pre‑ponderal evidence” (balance of evidence). | “Beyond a reasonable doubt” (high‑standard). |
| **Standard of proof** | “Pre‑ponderal evidence” – more likely than the other side. | “Beyond a reasonable doubt” – the evidence must be so strong that a reasonable person would be convinced. |
| **Procedure** | Civil courts (e.g., civil courts, arbitration, mediation). | Criminal courts (e.g., criminal courts, jury trials). |
| **Rights** | Plaintiff may sue for damages or inj. | Defendant has the right to a trial, counsel, and the presumption of innocence. |
| **Outcome** | The court orders the defendant to pay, or to do something. | The court orders the defendant to pay a fine, serve community service, or be imprisoned. |

**Key points**

1. **Who is suing?**  
   *Civil*: a private person or entity.  
   *Criminal*: the state (or the government) on behalf of society.

2. **What is being sought?**  
   *Civil*: compensation or a specific action.  
   *Criminal*: punishment for wrongdoing.

3. **Proof standard**  
   *Civil*: “balance of evidence.”  
   *Criminal*: “beyond a reasonable doubt.”

4. **Consequences**  
   *Civil*: monetary damages, injunctions, or restitution.  
   *Criminal*: fines, community service

---

Example 2

Question: Explain the concept of due process in legal systems.

Response:

<|channel|>analysis<|message|>Need explain due process.<|end|><|start|>assistant<|channel|>final<|message|>**Due Process (or “Due‑Process”) – the legal right to a fair, lawful treatment under the law**

---

### 1.  What is the concept?

* **Due process** is a constitutional or statutory safeguard that guarantees that a person, or a group, may be deprived of life, liberty, or property only through a fair, impartial, and lawful procedure.  
* It is a *procedual* right, not a *sub‑right* to a specific outcome.  The law must be followed, the rules must be applied, and the decision must be made by a competent, unbiased authority.

---

### 2.  Core elements

| Element | What it means | Why it matters |
|---|---|---|
| **Notice** | The person must be informed of the charges, claims, or actions against them. | Prevents surprise, allows preparation. |
| **Opportunity to respond** | The person must be given a chance to present evidence, argue, and cross‑cross witnesses. | Ensures the decision is based on a full record. |
| **Imse‑impartial decision maker** | The judge, magistrate, or other authority must be unbiased and independent. | Avoids arbitrary or politically motivated rulings. |
| **Reasoned decision** | The outcome must be explained, with a basis in the law and facts. | Allows review, appeals, and accountability. |
| **Right to appeal** | The person may challenge the decision in a higher court or tribunal. | Provides a safety net against errors. |
| **Procedual fairness** | The process must be conducted in a timely, orderly manner, respecting the rights of all parties. | Prevents abuse of power or delays that cause harm. |

---

### 3.  Why is it essential?

* **Rule of law** – It embodies the principle that the state may not act arbitrarily.  
* **Protection of minorities** – In plural societies, it safeguards the rights of the vulnerable, minorities, and dissenters.  
* **Legitimacy of the state** – A state that respects due process is seen as just, credible, and trustworthy.  
* **International law** – Many treaties (e.g., the Universal Declaration of Human Rights, the Convention on the Rights of the Child) embed due‑process principles.

---

### 4.  How it works in practice

| Country | Typical procedure | Key

---

Example 3

Question: What are the basic rights protected by the First Amendment?

Response:

<|channel|>analysis<|message|>Need to answer: rights: freedom from unreasonable searches, seizures, due due process, equal protection, freedom of speech, religion, press, assembly, petition, right to bear arms. Also right to privacy? Actually privacy not explicit. Provide list.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment is the first of the Bill of Rights and it protects a set of fundamental liberties that are considered essential to a free society.  In the text of the amendment itself, the most commonly cited “rights” are:

| **Freedom from unreasonable searches and seizures** | The government may not conduct a search or seizure of a person, property, or personal documents without a probable‑cause warrant. |
| **Due‑process (fair‑law) rights** | The government must follow a fair legal process before deprimin­ing a person’s life, liberty, or property. |
| **Equal‑protection** | No state may discriminate against a person on the basis of race, religion, or other protected characteristics. |
| **Freedom of speech** | Individuals may express opinions, ideas, and viewpoints without government censorship. |
| **Freedom of religion** | Individuals may practice, change, or abandon a religion without state interference. |
| **Freedom of press** | The press may publish news, opinions, and other information without government censorship. |
| **Freedom of assembly** | People may gather together for peaceful protest, demonstration, or other civic activities. |
| **Freedom to petition** | Citizens may petition the government for red‑action or red‑change. |
| **Right to bear arms** | The right to own and carry firearms (as interpreted by the Supreme Court). |

These are the core liberties that the First Amendment guarantees. The amendment also contains a “no‑law” clause that protects the right to “no‑law” (i.e., the right to be free from a law that is unconstitutional). In practice, the First Amendment is the foundation for many other rights that are protected by the Constitution, such as the right to privacy, the right to a fair trial, and the right to due‑process.<|return|>

---

Citation

If you use this model in your research, please cite:

@misc{priyanshu2025gptoss,
  title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
  author={Priyanshu, Aman and Vijay, Supriti},
  year={2025},
  howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
  note={Interactive analysis tool for expert activation patterns in MoE architectures}
}

References & Resources

• Original Model: OpenAI GPT-OSS Model Card
• Model Hub: GPT-OSS-20B on Hugging Face
• Expert Analysis Dataset: GPT-OSS-20B MoE Expert Activations
• Project Page: GPT-OSS MoE Expert Fingerprinting
• GitHub Repository: OpenAI GPT-OSS