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

    Neuronpedia

    APICircuit 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. 60822
    Prev
    Next
    INDEX
    Explanations

    build

    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
     reluct
    -0.08
    ęg
    -0.08
     Lle
    -0.08
    াটো
    -0.07
     freshmen
    -0.07
    Mor
    -0.07
    Encounter
    -0.07
     Patent
    -0.07
    ienz
    -0.07
     verstel
    -0.07
    POSITIVE LOGITS
    后的
    0.09
     geproduceerd
    0.09
    gatsby
    0.09
    .cleanup
    0.08
     output
    0.08
    退出
    0.08
    生成
    0.08
     produz
    0.08
     gerar
    0.08
     produire
    0.08
    Activations Density 0.003%

    No Known Activations