© 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. 111463
    Prev
    Next
    INDEX
    Explanations

    label

    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
     suff
    -0.08
     recreational
    -0.08
     eyeb
    -0.07
    Vision
    -0.07
     stal
    -0.07
     sav
    -0.07
     daim
    -0.07
    रेशन
    -0.07
    익
    -0.07
     rédu
    -0.07
    POSITIVE LOGITS
     Attached
    0.08
    olv
    0.08
    /licenses
    0.08
     Доп
    0.08
    ihan
    0.08
     बिक्री
    0.08
    billing
    0.08
     жасау
    0.08
    gee
    0.08
     MANAGEMENT
    0.08
    Activations Density 0.005%

    No Known Activations