© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78882
    Prev
    Next
    INDEX
    Explanations

    Covering and placement problems

    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
    -vol
    -0.10
     болон
    -0.09
     всех
    -0.08
    vol
    -0.08
     dals
    -0.08
    _namespace
    -0.08
     misdeme
    -0.07
     davon
    -0.07
     незакон
    -0.07
    .Article
    -0.07
    POSITIVE LOGITS
     couvr
    0.12
    Coverage
    0.12
     strategically
    0.11
     coverage
    0.11
     covering
    0.10
    coverage
    0.10
    Strateg
    0.10
     sufficient
    0.10
     Coverage
    0.09
    覆盖
    0.09
    Activations Density 0.028%

    No Known Activations