© 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. 95660
    Prev
    Next
    INDEX
    Explanations

    Petra architecture

    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
     remorse
    -0.08
     asp
    -0.08
    (cr
    -0.07
     ổ
    -0.07
     Roe
    -0.07
    (con
    -0.07
    .con
    -0.07
     remont
    -0.07
    微
    -0.07
     neighbourhood
    -0.07
    POSITIVE LOGITS
    glyph
    0.10
     glyph
    0.09
     欢
    0.08
     ата
    0.08
     тысячи
    0.08
     promin
    0.08
    ಖ
    0.08
     pauc
    0.07
     principale
    0.07
    APPY
    0.07
    Activations Density 0.002%

    No Known Activations