© 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. 44371
    Prev
    Next
    INDEX
    Explanations

    [

    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
     решили
    -0.08
     tucked
    -0.08
     perfection
    -0.07
     ME
    -0.07
     JSX
    -0.07
    Sul
    -0.07
     речи
    -0.07
     parlar
    -0.07
     прип
    -0.07
     gerade
    -0.07
    POSITIVE LOGITS
    |↵
    0.07
     partnership
    0.07
     making
    0.07
     effectiveness
    0.07
    매
    0.07
     Faça
    0.07
    116
    0.07
     makat
    0.07
     ETA
    0.07
     INTEGER
    0.07
    Activations Density 0.003%

    No Known Activations