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. 15-RESID-POST-AA
    6. 19183
    Prev
    Next
    INDEX
    Explanations

    say "the ending :"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     byose
    -0.10
     მხოლოდ
    -0.10
     სრული
    -0.10
     മാത്രം
    -0.10
    开奖记录
    -0.10
     بكل
    -0.10
     მატჩ
    -0.10
    免费看
    -0.10
     aðeins
    -0.10
     რე
    -0.09
    POSITIVE LOGITS
    如下
    0.20
    :↵↵
    0.14
     следующие
    0.14
    :↵↵
    0.13
     suivantes
    0.13
     revolves
    0.12
    以下
    0.12
     следующим
    0.12
     involves
    0.12
     suivants
    0.12
    Activations Density 0.041%

    No Known Activations