© 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. 23-RESID-POST-AA
    11. 96782
    Prev
    Next
    INDEX
    Explanations

    N

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ër
    -0.08
    α
    -0.08
    амъ
    -0.08
    әң
    -0.08
    siniz
    -0.08
    ありがとうございます
    -0.08
    _remove
    -0.08
    a
    -0.08
    It's
    -0.08
    ه
    -0.08
    POSITIVE LOGITS
    ominations
    0.10
    LEBeta
    0.10
    .Y
    0.10
    CAA
    0.09
    ominated
    0.08
    .W
    0.08
    ATION
    0.08
    278
    0.08
    887
    0.08
    ixon
    0.08
    Activations Density 0.020%

    No Known Activations