© 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. 78475
    Prev
    Next
    INDEX
    Explanations

    Excel

    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
     numerical
    -0.08
    weather
    -0.07
     वै
    -0.07
     missions
    -0.07
     gambler
    -0.07
     devast
    -0.07
     gaming
    -0.07
     भक्त
    -0.07
     dagar
    -0.07
     ';
    -0.07
    POSITIVE LOGITS
    рение
    0.09
     како
    0.09
     ұсыны
    0.07
    라고
    0.07
    링
    0.07
     ontstaat
    0.07
     entsteht
    0.07
    ريع
    0.07
    ль
    0.07
     commissie
    0.07
    Activations Density 0.001%

    No Known Activations