© 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. 24760
    Prev
    Next
    INDEX
    Explanations

    CSS box-shadow and border-radius

    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
     ഭൂ
    -0.07
     зн
    -0.07
    ോദ
    -0.07
     vivre
    -0.07
    (Material
    -0.07
     സ്വദേശ
    -0.07
    HAS
    -0.07
    РА
    -0.07
     CYP
    -0.07
    anes
    -0.07
    POSITIVE LOGITS
    █
    0.08
     report
    0.08
     ignore
    0.07
     Silent
    0.07
     perfil
    0.07
     complain
    0.07
    ignored
    0.07
    刺
    0.07
     rato
    0.07
     Stir
    0.07
    Activations Density 0.000%

    No Known Activations