© 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. 78881
    Prev
    Next
    INDEX
    Explanations

    modernism literature

    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
    เด็ก
    -0.08
     숙
    -0.08
     bilm
    -0.08
    ligt
    -0.07
    ref
    -0.07
    หว่าง
    -0.07
    leh
    -0.07
    ytorch
    -0.07
    Permutation
    -0.07
    ські
    -0.07
    POSITIVE LOGITS
     expend
    0.08
     impending
    0.08
    凯
    0.08
     loaf
    0.08
     화면
    0.08
     Gloria
    0.08
     खर्च
    0.07
     aspirations
    0.07
     guy
    0.07
     Gus
    0.07
    Activations Density 0.003%

    No Known Activations