© 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. 4
    Prev
    Next
    INDEX
    Explanations

    statistical medians and weights

    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
    shan
    -0.08
     προσπά
    -0.08
     intern
    -0.08
    .Pl
    -0.07
     coroutine
    -0.07
    .Now
    -0.07
     kế
    -0.07
    .Pow
    -0.07
     pipe
    -0.07
    .Move
    -0.07
    POSITIVE LOGITS
    _counts
    0.10
    人数
    0.10
     counts
    0.09
     fueling
    0.09
    Counts
    0.09
     cumplen
    0.08
     Surround
    0.08
     Everyone
    0.08
    остат
    0.08
    counts
    0.08
    Activations Density 0.010%

    No Known Activations