© 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. 99234
    Prev
    Next
    INDEX
    Explanations

    sa

    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
     работод
    -0.08
     trustees
    -0.08
     الأماكن
    -0.08
     arms
    -0.08
     arteries
    -0.08
     щ
    -0.07
     Tooth
    -0.07
     quen
    -0.07
     rifles
    -0.07
     Rush
    -0.07
    POSITIVE LOGITS
    یا
    0.09
    .Strict
    0.08
    iraz
    0.08
     berlangsung
    0.08
     Fakt
    0.08
     Augsburg
    0.07
    不知道
    0.07
    ying
    0.07
    atorio
    0.07
     gostei
    0.07
    Activations Density 0.001%

    No Known Activations