Caden Juang

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

Automatically Interpreting Millions of Features in Large Language Models

Automatically Interpreting Millions of Features in Large Language Models