{"total":12,"rows":[{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2602.04903","title":"Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2511.12240","title":"SCI: A Metacognitive Control for Signal Dynamics","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2605.16372","title":"SwordBench: Evaluating Orthogonality of Steering Image Representations","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.27158","title":"The Linear Representation Hypothesis Needs a Group Action","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}