© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64152
    Prev
    Next
    INDEX
    Explanations

    they

    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
    needs
    -0.09
    Needs
    -0.09
    .allocate
    -0.09
     spark
    -0.09
     needs
    -0.09
    ，需要
    -0.08
    <table
    -0.08
     NOR
    -0.08
    .alloc
    -0.07
     Banque
    -0.07
    POSITIVE LOGITS
     foll
    0.09
     Eigent
    0.08
     男女
    0.08
    ouncy
    0.08
     Sexy
    0.08
     ids
    0.08
     Emoji
    0.08
    зив
    0.08
    skrä
    0.08
     مذه
    0.08
    Activations Density 0.000%

    No Known Activations