AmanPriyanshu/gpt-oss-9.6b-specialized-law-pruned-moe-only-13-experts

Law GPT-OSS Model (13 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 13 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	~9.6B (pruned from 21B)
Original Experts per Layer	32
Pruned Experts per Layer	13
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 13 experts per layer
• No Retraining: Direct removal without additional training steps

Performance & Applications

Pruning Benefits

• Smaller Memory Footprint: 40.6% 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 13 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 13 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-9.6b-specialized-law-pruned-moe-only-13-experts", 
    torch_dtype=torch.bfloat16, 
    device_map="cpu", 
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-9.6b-specialized-law-pruned-moe-only-13-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-9.6b-specialized-law-pruned-moe-only-13-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-9.6b-specialized-law-pruned-moe-only-13-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 explain.<|end|><|start|>assistant<|channel|>final<|message|>**Civil law** and **criminal law** are two branches of the legal system that deal with very different kinds of disputes and wrongs.  The main differences lie in the parties involved, the purpose of the law, the burden of proof, the remedies, and the procedural rules.

| Feature | Civil Law | Criminal Law |
|---|---|---|
| **Parties** | Private individuals or entities (e.g., a person suing a neighbor for a property dispute, a company suing another for breach of contract). | The state (or society) versus an individual or entity accused of violating a statute (e.g., theft, assault). |
| **Purpose** | To resolve disputes between parties and to compensate the wrong‑party (damers) for loss or injury. | To punish or deter wrongdoing that harms society, to protect public order, and to maintain social safety. |
| **Burain of Proof** | “Pre‑beyond a reasonable doubt” is not required; the plaintiff must prove the claim **by a pre‑balance of evidence** (i.e., “more likely than less”). | The prosecution must prove the defendant’s guilt **beyond a reasonable doubt**. |
| **Remade** | Typically monetary damages, injunctions, or specific performance (e.g., pay compensation, stop a nuisance). | Penative sanctions: fines, imprisonment, probation, community service, restitution, or other corrective measures. |
| **Procedure** | Usually civil courts or tribunals; parties may choose to represent themselves or hire counsel; the process is often less formal and can be faster. | Criminal courts (often with a judge and jury); the defendant has constitutional rights (e‑e. right to counsel, right to a speedy trial, right to a presis). The process is more formal and can be longer. |
| **Defender’s Rights** | The defendant (or “respondent”) has a right to a fair hearing, but the state does not have a special “prosecution” role. | The defendant has a right to a presis, to counsel, to cross‑examination, to a jury, and to appeal. |
| **Outcome** | The court orders the defendant to pay or to do something; the plaintiff receives compensation. | The court orders the defendant to pay a fine, serve jail time, or perform community service. |
| **Examples** | Contract disputes, property disputes, tort claims (neglig

---

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”) – a Fundamental Legal Principle**

---

### 1. What it Is  
* **Due Process** is a constitutional or statutory safeguard that guarantees a fair, impartial, and transparent legal procedure before the state may deprim­ent an individual’s life, liberty, or property.  
* It is a *procedural* right, not a substantive right. It protects the *process* by which a government acts, not the outcome itself.

---

### 2. Core Elements  
| Element | Why It Matters | Typical Manifestation |
|--------|--------------|------------------------|
| **Notice** | The person must be informed of the claim or charge. | Written summons, court docket, public notice. |
| **Opportunity to Respond** | The person must be able to present evidence, argue, and cross‑examine. | Oral or written pleadings, deposition, trial. |
| **Neutral Decision Maker** | The decision must be made by an impartial judge or jury. | Ad‑un‑parte judge, jury trial. |
| **Right to Counsel** | The person may have legal representation. | Public‑law attorney, private counsel. |
| **Right to Appeal** | The decision can be reviewed by a higher court. | Appeal, habe‑de‑liba, appellate review. |
| **Reasoned Decision** | The outcome must be based on evidence and law. | Written opinion, record of findings. |
| **Timity** | The process must be timely, preventing indefinite detention or punishment. | Stat‑tim, bail, release. |

---

### 3. Historical Roots  

| Era | Key Development |
|-----|----------------|
| **17th–18th Century** | English Common Law – “no law without the consent of the people.” |
| **19th Century** | U.S. Constitution (17th Amendment) – “no law shall be passed without the consent of the people.” |
| **20th Century** | 4th & 5th Amendments (U.S.) – “No person shall be deprived of life, liberty, or property … without due process.” |
| **International** | Universal Declaration of Human Rights (1945) – “Everyone has the right to a fair trial.” |

---

### 4. How It Works in Practice  

1. **Arar‑diction** – The state must show a

---

Example 3

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

Response:

<|channel|>analysis<|message|>Need to answer: rights: freedom of religion, freedom of speech, press, assembly, petition, right to bear arms? Actually 1st Amendment: prohibits laws abrapping religion, speech, press, assembly, petition, and also right to bear arms. Provide explanation.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment to the U.S. Constitution protects a handful of fundamental civil liberties that are considered essential to a free, democratic society.  In short, it guarantees:

| **Right** | **What it protects** |
|---|---|
| **Freedom of Religion** | The government may not establish a religion or prohibit the practice of any religion. |
| **Freedom of Speech** | Individuals may express opinions, ideas, and viewpoints without government censorship or punishment. |
| **Freedom of the Press** | The press (newspapers, radio, television, etc.) may publish information and critique the government. |
| **Freedom of Assembly** | People may gather peacefully for protest, demonstration, or other purposes. |
| **Freedom to Petition** | Citizens may request or demand action from the government. |
| **Right to Bear Arms** | (as interpreted by the Supreme Court) Individuals may possess and carry firearms. |

These rights are not absolute; the courts have carved out certain limits (e.g., restrictions on hate‑speech, defamation, obscus­ity, or threats of violence).  But the First Amendment remains the cornerstone of American free‑speech, religious liberty, and democratic participation.<|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