© 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. 113608
    Prev
    Next
    INDEX
    Explanations

    kind

    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
    ============↵
    -0.09
    initions
    -0.09
    ۇل
    -0.08
     beleggen
    -0.08
    stead
    -0.08
     uban
    -0.08
     tilgjeng
    -0.08
     hingga
    -0.08
     sidoo
    -0.08
     velit
    -0.08
    POSITIVE LOGITS
    Pe
    0.08
     Pe
    0.07
    Var
    0.07
    op
    0.07
     Keep
    0.07
     Adam
    0.07
     Leon
    0.07
    0.07
    år
    0.07
     Key
    0.07
    Activations Density 1.734%
    No Known Activations