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. 111723
    Prev
    Next
    INDEX
    Explanations

    suicidal thoughts

    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
     Lumi
    -0.08
    Ledger
    -0.08
     Kuh
    -0.07
     səh
    -0.07
     gue
    -0.07
    jum
    -0.07
     businessmen
    -0.07
     LLVM
    -0.07
    _formula
    -0.07
    _extra
    -0.07
    POSITIVE LOGITS
     угроз
    0.09
     threatens
    0.08
     нарушения
    0.08
     warrant
    0.08
     imminent
    0.08
     ప్రమాద
    0.08
     risks
    0.08
     pangan
    0.08
     наруш
    0.08
     threats
    0.08
    Activations Density 0.004%

    No Known Activations