© 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. 29134
    Prev
    Next
    INDEX
    Explanations

    Flatten

    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
     nás
    -0.08
     jeopard
    -0.07
    acular
    -0.07
     audiovisual
    -0.07
     crystall
    -0.07
     figur
    -0.07
    abcdefghijklmnopqrstuvwxyz
    -0.07
    -items
    -0.07
    Kan
    -0.07
    Canc
    -0.07
    POSITIVE LOGITS
     энд
    0.08
     الشمس
    0.08
     messen
    0.08
     stad
    0.08
     прил
    0.08
     slag
    0.08
     إج
    0.08
     erine
    0.08
     айыр
    0.08
     Над
    0.08
    Activations Density 0.001%

    No Known Activations