© 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. 45261
    Prev
    Next
    INDEX
    Explanations

    structured explanations

    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
     사람이
    -0.08
    typically
    -0.07
    [selected
    -0.07
    님
    -0.07
    SELECT
    -0.07
    INSERT
    -0.07
     фар
    -0.07
     ხ
    -0.07
     пир
    -0.07
     TORT
    -0.07
    POSITIVE LOGITS
    .Collection
    0.09
    重点
    0.08
    supp
    0.07
    ，以及
    0.07
    edik
    0.07
    asas
    0.07
    ARDS
    0.07
    kamp
    0.07
     overview
    0.07
    /actions
    0.07
    Activations Density 0.155%

    No Known Activations