SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

arXiv:2609.09113 · cs.AI, cs.CL, cs.LG · Submitted 2026-09-08 · Read on arXiv

cs.AI, cs.CL, cs.LG

Submitted: 2026-09-08

Updated: 2026-09-11

Comments: Preprint. Work in Progress

Code: https://github.com/Trae1ounG/SAEScientist

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 3× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes
• Sparse Autoencoders (SAEs) — 1× in this paper · explained in 3 episodes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection