© 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. 11-RESID-POST-AA
    6. 95638
    Prev
    Next
    INDEX
    Explanations

    _model

    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
    嫁
    -0.09
     prune
    -0.08
     spouse
    -0.08
     SINGLE
    -0.08
    (chunk
    -0.08
     stitch
    -0.08
     我要
    -0.08
    :hidden
    -0.07
     tramo
    -0.07
    合法
    -0.07
    POSITIVE LOGITS
     Creates
    0.08
     characteristic
    0.07
    uds
    0.07
     throughout
    0.07
    asje
    0.07
     bezpieczeń
    0.07
    155
    0.07
    056
    0.07
     исп
    0.07
    /name
    0.07
    Activations Density 0.001%

    No Known Activations