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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108609
    Prev
    Next
    INDEX
    Explanations

    层

    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
    น์
    -0.09
    ต์
    -0.09
     additive
    -0.08
     Moder
    -0.08
     moder
    -0.08
    ท์
    -0.08
    Indexed
    -0.08
     moderately
    -0.08
    .sid
    -0.08
    tyard
    -0.08
    POSITIVE LOGITS
    人士
    0.09
    तम
    0.08
     अक
    0.07
    尚
    0.07
    机关
    0.07
    MOST
    0.07
    তম
    0.07
    775
    0.07
    学历
    0.07
    ावत
    0.07
    Activations Density 0.012%

    No Known Activations