© 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. 48842
    Prev
    Next
    INDEX
    Explanations

    Instructions, code, abbreviations

    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
    _ball
    -0.08
     берег
    -0.08
     IE
    -0.07
     într
    -0.07
     dovrebbe
    -0.07
     gị
    -0.07
    ీ
    -0.07
     weary
    -0.07
     desperately
    -0.07
    зе
    -0.07
    POSITIVE LOGITS
    erc
    0.08
    ndir
    0.08
    arked
    0.08
    料金
    0.08
    Rated
    0.08
    andbox
    0.07
    gram
    0.07
    @No
    0.07
     Cinco
    0.07
    asol
    0.07
    Activations Density 0.000%

    No Known Activations