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. 53161
    Prev
    Next
    INDEX
    Explanations

    identification forms

    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
     call
    -0.09
    big
    -0.08
     treatment
    -0.07
     big
    -0.07
     ibikorwa
    -0.07
    23
    -0.07
     smashing
    -0.07
     midfielder
    -0.07
    ,k
    -0.07
    -big
    -0.07
    POSITIVE LOGITS
    身份证
    0.10
     удостовер
    0.10
     സ്ഥിരീകര
    0.09
     പരിശോധന
    0.09
    .verify
    0.08
    เลือ
    0.08
     আপ
    0.08
    eid
    0.08
     GED
    0.08
     überprü
    0.08
    Activations Density 0.022%

    No Known Activations