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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 67606
    Prev
    Next
    INDEX
    Explanations

    Comma separated numbers

    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
     TRE
    -0.08
    .prototype
    -0.08
     Noah
    -0.08
     Barrier
    -0.07
    irer
    -0.07
    iffe
    -0.07
    ाने
    -0.07
     ゴ
    -0.07
     Discussions
    -0.07
     Trait
    -0.07
    POSITIVE LOGITS
     στις
    0.08
     palpable
    0.08
    _clusters
    0.07
     än
    0.07
    聯
    0.07
     vollständ
    0.07
     imme
    0.07
     свидетель
    0.07
    Intervals
    0.07
     means
    0.07
    Activations Density 0.008%

    No Known Activations