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. 59275
    Prev
    Next
    INDEX
    Explanations

    Math expressions

    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
    フォ
    -0.08
    Pr
    -0.08
    prav
    -0.07
    umna
    -0.07
    .magic
    -0.07
    778
    -0.07
     offr
    -0.07
     öl
    -0.07
    納
    -0.07
     எதிர
    -0.07
    POSITIVE LOGITS
     способности
    0.09
    .Border
    0.08
    ಿಂ
    0.08
     себе
    0.08
    က်
    0.08
     sle
    0.07
     cot
    0.07
    ಕ್ತ
    0.07
     частности
    0.07
    riert
    0.07
    Activations Density 0.224%

    No Known Activations