© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 103407
    Prev
    Next
    INDEX
    Explanations

    =>

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵↵
    -0.21
    ।↵↵
    -0.17
    ۔↵↵
    -0.17
    。↵↵
    -0.16
    .↵
    -0.14
    ?↵↵
    -0.14
     .↵↵
    -0.13
    ։↵↵
    -0.13
    !↵↵
    -0.13
    :↵↵
    -0.13
    POSITIVE LOGITS
     implies
    0.12
    /oder
    0.11
     سپس
    0.11
     ydy
    0.11
     پوءِ
    0.11
     vervolgens
    0.11
     ...)
    0.11
     rearr
    0.11
     then
    0.11
     luego
    0.11
    Activations Density 0.039%

    No Known Activations