© 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. 65366
    Prev
    Next
    INDEX
    Explanations

    Polydipsia

    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
    争
    -0.08
     konfl
    -0.08
    adians
    -0.08
     "["
    -0.08
    阻
    -0.08
     विवाद
    -0.08
     vur
    -0.08
     blockage
    -0.07
    ांश
    -0.07
     secondaires
    -0.07
    POSITIVE LOGITS
     Sprite
    0.08
     habit
    0.08
    RTL
    0.08
     liebt
    0.08
    ooli
    0.07
    illow
    0.07
    بيع
    0.07
     appetite
    0.07
     مشهور
    0.07
    .ac
    0.07
    Activations Density 0.004%

    No Known Activations