© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 48030
    Prev
    Next
    INDEX
    Explanations

    Medical symptoms and stroke

    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
    immutable
    -0.08
     Andersen
    -0.07
    reuse
    -0.07
     jumbo
    -0.07
    linky
    -0.07
     کړی
    -0.07
    ’él
    -0.07
    akar
    -0.07
    Louis
    -0.07
    _Label
    -0.07
    POSITIVE LOGITS
     symptoms
    0.16
     symptomen
    0.14
     أعراض
    0.14
     Symptoms
    0.14
     Symptome
    0.13
     симптомы
    0.13
     symptom
    0.13
    症
    0.13
     sintomas
    0.13
     síntomas
    0.12
    Activations Density 0.071%

    No Known Activations