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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30989
    Prev
    Next
    INDEX
    Explanations

    extra payments

    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
    nin
    -0.08
     zapew
    -0.07
    nipeg
    -0.07
    yne
    -0.07
    gry
    -0.07
    maze
    -0.07
    jamin
    -0.07
    keeper
    -0.07
    ிலையில்
    -0.07
     guarded
    -0.07
    POSITIVE LOGITS
     बोनस
    0.09
     زیات
    0.09
     бонус
    0.09
     sterker
    0.09
     stronger
    0.08
     annually
    0.08
    本金
    0.08
     Bonuses
    0.08
     अतिरिक्त
    0.08
     વધારો
    0.08
    Activations Density 0.005%

    No Known Activations