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

    Neuronpedia

    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. 45414
    Prev
    Next
    INDEX
    Explanations

    produce

    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
    Fatal
    -0.08
    ..."↵
    -0.08
    ...",↵
    -0.08
    深入
    -0.07
    戸
    -0.07
     approfond
    -0.07
     fatal
    -0.07
     столк
    -0.07
    =true
    -0.07
    .Det
    -0.07
    POSITIVE LOGITS
     punctuation
    0.11
     Typ
    0.09
     typing
    0.09
     mashed
    0.08
     Revised
    0.08
     pronunciation
    0.08
    semicolon
    0.08
     Updated
    0.08
     revised
    0.08
     Display
    0.07
    Activations Density 0.042%

    No Known Activations