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. 12181
    Prev
    Next
    INDEX
    Explanations

    medical alerts

    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
     profitability
    -0.09
     varn
    -0.08
     Einfluss
    -0.07
     תנ
    -0.07
     renovating
    -0.07
     وحدة
    -0.07
    盈利
    -0.07
    Unt
    -0.07
     yards
    -0.07
     spectator
    -0.07
    POSITIVE LOGITS
     emergencies
    0.12
     emergency
    0.10
    报警
    0.10
     Emergency
    0.10
    alerts
    0.09
    Emergency
    0.09
     Panic
    0.09
     Alerts
    0.09
    ergency
    0.09
    Alerts
    0.09
    Activations Density 0.020%

    No Known Activations