© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 110032
    Prev
    Next
    INDEX
    Explanations

    Geometry reflections

    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
    Negative Logits
    ুলো
    -0.08
    まだ
    -0.08
     ration
    -0.08
     dashboards
    -0.07
    กัด
    -0.07
    け
    -0.07
    ulação
    -0.07
     livelihoods
    -0.07
     livelihood
    -0.07
     cessation
    -0.07
    POSITIVE LOGITS
    reflection
    0.11
     reflexión
    0.10
     réflexion
    0.10
     reflector
    0.09
     reflexão
    0.09
     reflection
    0.09
    transpose
    0.09
     отраж
    0.09
     réflex
    0.09
     reflected
    0.09
    Activations Density 0.015%

    No Known Activations