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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120304
    Prev
    Next
    INDEX
    Explanations

    error codes

    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
    Projectile
    -0.08
     bed
    -0.08
     hemis
    -0.08
     Hok
    -0.08
     projectile
    -0.08
     sculpt
    -0.08
     Stockholm
    -0.07
     hedge
    -0.07
    .capitalize
    -0.07
     roof
    -0.07
    POSITIVE LOGITS
    (errno
    0.12
     HRESULT
    0.11
     troubleshoot
    0.11
     troubleshooting
    0.11
     Troubles
    0.11
     오류
    0.11
    "errors
    0.11
     errno
    0.10
    错误
    0.10
     symptoms
    0.10
    Activations Density 0.020%

    No Known Activations