© 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. 11-RESID-POST-AA
    11. 65555
    Prev
    Next
    INDEX
    Explanations

    data

    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
     dipl
    -0.09
    狠狠
    -0.08
    敢
    -0.08
     Holt
    -0.07
    寒
    -0.07
     lill
    -0.07
     ack
    -0.07
    .dim
    -0.07
    ternoons
    -0.07
    viz
    -0.07
    POSITIVE LOGITS
     воздействия
    0.09
    [data
    0.09
    да
    0.08
     unite
    0.08
    [href
    0.08
     воздейств
    0.08
    _CONTAINER
    0.08
     потен
    0.08
    (trigger
    0.08
    trigger
    0.08
    Activations Density 0.003%

    No Known Activations