© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113618
    Prev
    Next
    INDEX
    Explanations

    Anchoring bias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Present
    -0.08
    present
    -0.07
     Submission
    -0.07
    زاز
    -0.07
     llor
    -0.07
     incision
    -0.07
     accompaniment
    -0.07
    תם
    -0.07
     наш
    -0.07
     magnets
    -0.07
    POSITIVE LOGITS
     estates
    0.10
     Aub
    0.08
     træ
    0.08
     Advice
    0.08
     Estate
    0.08
     Wealth
    0.08
     transfér
    0.08
     estate
    0.08
     Uniform
    0.08
     الدرا
    0.07
    Activations Density 0.006%

    No Known Activations