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. 12076
    Prev
    Next
    INDEX
    Explanations

    Checking for errors

    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
    282
    -0.08
     conj
    -0.07
     बिग
    -0.07
     управ
    -0.07
     Управ
    -0.07
     interesting
    -0.07
     огранич
    -0.07
     limited
    -0.07
     хар
    -0.07
     محدود
    -0.07
    POSITIVE LOGITS
     പരിശോധന
    0.15
     Провер
    0.15
     proofreading
    0.15
    チェック
    0.14
    _checks
    0.14
    -check
    0.14
     Checks
    0.14
    检查
    0.14
    Checks
    0.14
     যাচ
    0.14
    Activations Density 0.045%

    No Known Activations