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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11674
    Prev
    Next
    INDEX
    Explanations

    search algorithms

    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
     génére
    -0.11
     regen
    -0.10
     generosity
    -0.09
     upgr
    -0.09
     holland
    -0.09
    Vat
    -0.09
     acredit
    -0.09
    情色
    -0.09
    创
    -0.09
     furl
    -0.08
    POSITIVE LOGITS
     searching
    0.15
    Searching
    0.15
     searched
    0.14
     searches
    0.13
     search
    0.13
     Searching
    0.13
     검색
    0.13
     Searches
    0.13
    検索
    0.13
    .Search
    0.12
    Activations Density 0.012%

    No Known Activations