© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96342
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    用
    -0.07
    CALE
    -0.07
     Себ
    -0.07
     upstream
    -0.07
    쇄
    -0.07
    _far
    -0.07
     IX
    -0.07
    USH
    -0.07
    /look
    -0.07
     Encoder
    -0.07
    POSITIVE LOGITS
    .Q
    0.09
    .Department
    0.08
     Q
    0.08
    .department
    0.08
    imits
    0.08
    <Q
    0.08
     department
    0.08
    tium
    0.08
     gé
    0.08
     Denmark
    0.08
    Activations Density 0.001%

    No Known Activations