© 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. 129452
    Prev
    Next
    INDEX
    Explanations

    billing and payment

    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
     obscure
    -0.08
    -big
    -0.08
     restoration
    -0.08
    Disappear
    -0.07
    .fade
    -0.07
     disappearing
    -0.07
     Fade
    -0.07
     fade
    -0.07
    _rest
    -0.07
     dynamic
    -0.07
    POSITIVE LOGITS
     điện
    0.09
     eur
    0.08
     hous
    0.08
     الدفع
    0.08
     iliş
    0.08
     юрид
    0.08
     mă
    0.08
     verplicht
    0.08
     پرداخت
    0.08
     elektronik
    0.08
    Activations Density 0.011%

    No Known Activations