© 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 EvalsExportsinterp-engineNEWAPI 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. 70385
    Prev
    Next
    INDEX
    Explanations

    Code and parameters

    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
     చేస
    -0.07
     bookkeeping
    -0.07
     belongings
    -0.07
     субъект
    -0.07
     항상
    -0.07
    Mel
    -0.07
    ოშ
    -0.07
    ობლ
    -0.07
     beforehand
    -0.07
     demographics
    -0.07
    POSITIVE LOGITS
     Turbo
    0.08
     turbo
    0.08
    gressive
    0.08
    Turbo
    0.08
    Expo
    0.07
    Roof
    0.07
     wyk
    0.07
     roof
    0.07
    이버
    0.07
     roofing
    0.07
    Activations Density 35.257%

    No Known Activations