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. 102978
    Prev
    Next
    INDEX
    Explanations

    prime

    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
    ается
    -0.08
     killed
    -0.08
    _relation
    -0.08
     улар
    -0.08
     ಬದುಕ
    -0.08
    ्रीय
    -0.07
    KY
    -0.07
     биздин
    -0.07
     bleibt
    -0.07
     टूट
    -0.07
    POSITIVE LOGITS
     plants
    0.08
     watchers
    0.07
    419
    0.07
     Dank
    0.07
    43
    0.07
     seleccion
    0.07
     watchdog
    0.07
    .rand
    0.07
     cuidadosamente
    0.07
     factors
    0.07
    Activations Density 0.001%

    No Known Activations