Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29814
    Prev
    Next
    INDEX
    Explanations

    USD

    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
     Stalin
    -0.08
    Vom
    -0.08
     Unt
    -0.07
     svensk
    -0.07
    چه
    -0.07
    isure
    -0.07
     drunk
    -0.07
    odh
    -0.07
    炮
    -0.07
    chantment
    -0.07
    POSITIVE LOGITS
    USD
    0.08
     desg
    0.08
    ottages
    0.08
    0.08
     Chen
    0.08
     dollars
    0.08
     confortable
    0.07
     الأمريكية
    0.07
    sanitize
    0.07
     Yen
    0.07
    Activations Density 0.010%

    No Known Activations