© 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. 54908
    Prev
    Next
    INDEX
    Explanations

    Songkran festival

    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
    规律
    -0.07
    _the
    -0.07
     आवश्यक
    -0.07
     distractions
    -0.07
     mechan
    -0.07
     Greene
    -0.07
     omissions
    -0.07
    分别
    -0.07
    任务
    -0.07
    ##↵
    -0.07
    POSITIVE LOGITS
     Tribut
    0.09
     Workbook
    0.08
     Amaz
    0.08
     nourishment
    0.08
     Agricultura
    0.08
     MMC
    0.08
     nourishing
    0.08
    rch
    0.08
     پانی
    0.08
     Traditionally
    0.08
    Activations Density 0.003%

    No Known Activations