© 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. 44860
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Arab
    -0.07
    BD
    -0.07
    icí
    -0.07
     coarse
    -0.07
    ATER
    -0.07
    _generic
    -0.07
    ারা
    -0.07
     ko
    -0.07
    ographies
    -0.07
    提
    -0.07
    POSITIVE LOGITS
     фон
    0.10
     kõ
    0.09
     мит
    0.08
     {↵↵/
    0.08
     Fos
    0.08
     luid
    0.08
     кеш
    0.08
     anymore
    0.08
      
    0.08
           ↵
    0.08
    Activations Density 0.013%

    No Known Activations