Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 106100
    Prev
    Next
    INDEX
    Explanations

    red

    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
    资料
    -0.08
     marge
    -0.08
    流程
    -0.08
    idean
    -0.07
    特殊
    -0.07
     tund
    -0.07
    peł
    -0.07
    人體
    -0.07
     δί
    -0.07
     personalise
    -0.07
    POSITIVE LOGITS
    Wins
    0.08
    Balls
    0.08
     Kendall
    0.08
     vs
    0.07
    Count
    0.07
    Puzzle
    0.07
    Stat
    0.07
    Counts
    0.07
     LEGO
    0.07
    /red
    0.07
    Activations Density 0.009%

    No Known Activations