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. 58734
    Prev
    Next
    INDEX
    Explanations

    202

    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
    猎
    -0.08
    .M
    -0.08
     hunter
    -0.07
    )-(
    -0.07
     hunters
    -0.07
     +
    -0.07
    VER
    -0.07
     patron
    -0.07
     driver
    -0.07
    -based
    -0.07
    POSITIVE LOGITS
    (bitmap
    0.08
     کل
    0.08
    有限公司
    0.08
    δά
    0.08
    uidado
    0.08
    ardoor
    0.07
     }],↵
    0.07
    ਾਇਆ
    0.07
     Navarro
    0.07
     doonaa
    0.07
    Activations Density 0.145%

    No Known Activations