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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43512
    Prev
    Next
    INDEX
    Explanations

    physical therapy

    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
    Opening
    -0.10
    Fixture
    -0.09
     opening
    -0.09
    opening
    -0.08
     Opening
    -0.08
    Fixtures
    -0.08
    _feature
    -0.08
    Feature
    -0.08
    ose
    -0.08
     Investigación
    -0.07
    POSITIVE LOGITS
    히
    0.08
     самостоятель
    0.08
    复制
    0.08
     самостоятельно
    0.08
    ไป
    0.08
     дальней
    0.08
     trained
    0.08
     Mittel
    0.07
    barth
    0.07
    0.07
    Activations Density 0.016%
    No Known Activations