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. 65232
    Prev
    Next
    INDEX
    Explanations

    身份 (identity)

    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
     encarg
    -0.08
     أح
    -0.08
     ماد
    -0.08
     abdomen
    -0.08
     Nouveau
    -0.08
    ходит
    -0.08
     clockwise
    -0.08
     Forget
    -0.08
     اخ
    -0.08
     Hai
    -0.08
    POSITIVE LOGITS
    .authenticate
    0.08
     শন
    0.08
     ಗುರು
    0.08
    /login
    0.07
    ’identité
    0.07
     পরিচ
    0.07
    নীত
    0.07
    entication
    0.07
    .git
    0.07
     সংগ্র
    0.07
    Activations Density 0.006%

    No Known Activations