# SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models

arXiv: https://arxiv.org/abs/2511.20820 · HTML: https://mlsanity.com/paper/2511.20820/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

## Builds on (most cited first, 17 of 17)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Sparse Overcomplete Word Vector Representations](https://mlsanity.com/paper/1506.02004/) (2015)
- [Interpreting Attention Layer Outputs with Sparse Autoencoders](https://mlsanity.com/paper/2406.17759/) (2024)
- [Enhancing Automated Interpretability with Output-Centric Feature Descriptions](https://mlsanity.com/paper/2501.08319/) (2025)
- [SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models](https://mlsanity.com/paper/2505.16188/) (2025)
- [Understanding Refusal in Language Models with Sparse Autoencoders](https://mlsanity.com/paper/2505.23556/) (2025)
- [Route Sparse Autoencoder to Interpret Large Language Models](https://mlsanity.com/paper/2503.08200/) (2025)
- [Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms](https://mlsanity.com/paper/2505.20322/) (2025)
- [Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders](https://mlsanity.com/paper/2502.15576/) (2025)
- [Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training](https://mlsanity.com/paper/2505.14681/) (2025)
- [Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification](https://mlsanity.com/paper/2502.14133/) (2025)
- [KnowThyself: An Agentic Assistant for LLM Interpretability](https://mlsanity.com/paper/2511.03878/) (2025)

## Built on by (most cited first, 10 of 10)

- [All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs](https://mlsanity.com/paper/2605.12671/) (2026)
- [Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs](https://mlsanity.com/paper/2603.03415/) (2026)
- [Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing](https://mlsanity.com/paper/2604.15771/) (2026)
- [Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features](https://mlsanity.com/paper/2605.12874/) (2026)
- [Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence](https://mlsanity.com/paper/2608.12036/) (2026)
- [Agentic-imodels: Evolving agentic interpretability tools via autoresearch](https://mlsanity.com/paper/2605.03808/) (2026)
- [Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent](https://mlsanity.com/paper/2607.16448/) (2026)
- [SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization](https://mlsanity.com/paper/2608.13538/) (2026)
- [SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?](https://mlsanity.com/paper/2609.09113/) (2026)
- [From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features](https://mlsanity.com/paper/2609.35367/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have emerged as a promising tool for decomposing LLM representations into more interpretable features, but explaining the features captured by SAEs remains a challenging task. In this work, we propose SAGE (SAE AGentic Explainer), an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanation-driven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an active, explanationdriven process. SAGE implements a rigorous methodology by systematically formulating multiple explanations for each feature, designing targeted experiments to test them, and iteratively refining explanations based on empirical activation feedback. Experiments on features from SAEs of diverse language models demonstrate that SAGE produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines.