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. 102810
    Prev
    Next
    INDEX
    Explanations

    mental health diagnosis

    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
     shafts
    -0.10
     manifestó
    -0.09
     railing
    -0.08
     участка
    -0.08
    .zaxxer
    -0.08
    -address
    -0.08
    LLU
    -0.08
     Deel
    -0.08
     владель
    -0.08
    .vert
    -0.08
    POSITIVE LOGITS
     schizophrenia
    0.13
     psychiatric
    0.13
     autism
    0.12
     ICD
    0.12
     diagnoses
    0.11
     psychopath
    0.11
    診
    0.10
     diagnosis
    0.10
     standardized
    0.10
    taxonomy
    0.10
    Activations Density 0.021%

    No Known Activations