© 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. 23-RESID-POST-AA
    6. 5366
    Prev
    Next
    INDEX
    Explanations

    gem or game

    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
    类型
    -0.08
     type
    -0.08
    辅
    -0.08
    (type
    -0.08
    .set
    -0.07
    	type
    -0.07
     set
    -0.07
     kind
    -0.07
    零
    -0.07
    粗
    -0.07
    POSITIVE LOGITS
    :Get
    0.11
    .config
    0.09
    .paths
    0.09
    _gener
    0.09
    _package
    0.08
    _path
    0.08
     ukusebenza
    0.08
    جن
    0.08
    _runtime
    0.08
     موتور
    0.08
    Activations Density 0.000%

    No Known Activations