Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11775
    Prev
    Next
    INDEX
    Explanations

    Video games

    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
    Anc
    -0.08
    _un
    -0.08
     Ancient
    -0.08
    änger
    -0.07
     unw
    -0.07
    three
    -0.07
     difficile
    -0.07
    OK
    -0.07
     exp
    -0.07
     ancient
    -0.07
    POSITIVE LOGITS
     realism
    0.09
     competição
    0.09
    前年
    0.09
    ,今年
    0.09
     Forecast
    0.09
     Sports
    0.09
    -comment
    0.09
     Week
    0.09
    (updated
    0.08
     Season
    0.08
    Activations Density 0.006%

    No Known Activations