© 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. 78131
    Prev
    Next
    INDEX
    Explanations

    hardware pins

    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
     vigorous
    -0.09
     enjoyable
    -0.08
     nltk
    -0.08
    .Ap
    -0.08
    /news
    -0.08
     vivid
    -0.08
    发表于
    -0.07
    luc
    -0.07
    坚定
    -0.07
     kr
    -0.07
    POSITIVE LOGITS
    wire
    0.10
     disposición
    0.10
     वायर
    0.09
     solder
    0.09
    Wire
    0.09
     Wire
    0.09
     Wiring
    0.09
    _wire
    0.09
     배열
    0.08
     الكهربائية
    0.08
    Activations Density 0.007%

    No Known Activations