© 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. 71289
    Prev
    Next
    INDEX
    Explanations

    Bordeaux

    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
     thousand
    -0.08
     ఎన్న
    -0.08
    //=
    -0.08
    േക്ഷ
    -0.08
     shug
    -0.07
     marinade
    -0.07
    ылым
    -0.07
     oo
    -0.07
     cane
    -0.07
     meaningless
    -0.07
    POSITIVE LOGITS
    Tv
    0.08
    Pal
    0.08
     Tv
    0.08
     Dante
    0.08
    _pal
    0.08
    Rome
    0.08
    ftp
    0.07
     Mohammad
    0.07
     Vol
    0.07
     Pal
    0.07
    Activations Density 0.630%

    No Known Activations