© 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. 114215
    Prev
    Next
    INDEX
    Explanations

    sans

    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
     Reve
    -0.09
    endez
    -0.08
    了解到
    -0.08
     Поз
    -0.07
     Einkommen
    -0.07
    金币
    -0.07
    כה
    -0.07
     negativas
    -0.07
     જાણવા
    -0.07
     contagious
    -0.07
    POSITIVE LOGITS
    -serif
    0.10
    /tab
    0.09
    -tab
    0.09
    .today
    0.08
    -white
    0.08
     sans
    0.08
    -flat
    0.08
    .selected
    0.08
     Arial
    0.08
    :white
    0.07
    Activations Density 0.001%

    No Known Activations