© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
    -ts
    -0.08
    .you
    -0.08
    sns
    -0.08
     Tener
    -0.07
     LABEL
    -0.07
     Hatch
    -0.07
    Tol
    -0.07
     label
    -0.07
    LABEL
    -0.07
    _Per
    -0.07
    POSITIVE LOGITS
    ированной
    0.09
     наоборот
    0.09
     disparition
    0.09
     называется
    0.09
     positively
    0.09
     positiven
    0.08
     positive
    0.08
    称
    0.08
    positive
    0.08
     contrário
    0.08
    Activations Density 0.206%

    No Known Activations