© 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. 113266
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
    行政
    -0.09
    ，如
    -0.08
    চ্ছ
    -0.08
    ে
    -0.08
    撑
    -0.08
     goodwill
    -0.08
     Administrative
    -0.08
     Toto
    -0.08
    ค้า
    -0.08
     administratif
    -0.08
    POSITIVE LOGITS
    `,
    0.07
     Da
    0.07
     mc
    0.07
     kan
    0.07
     Wen
    0.07
     WH
    0.07
     Won
    0.07
     rat
    0.07
     Nu
    0.07
     Cy
    0.07
    Activations Density 0.003%

    No Known Activations