© 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. 71650
    Prev
    Next
    INDEX
    Explanations

    sit

    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
     proves
    -0.08
    Ot
    -0.08
     inning
    -0.08
    Cb
    -0.08
     Ot
    -0.07
     escola
    -0.07
     Sank
    -0.07
     jealousy
    -0.07
     ot
    -0.07
    afia
    -0.07
    POSITIVE LOGITS
     Universal
    0.09
     firm
    0.08
     naka
    0.08
     מור
    0.08
     firmly
    0.08
     quiet
    0.08
     shallow
    0.08
    extr
    0.08
     universal
    0.07
     quas
    0.07
    Activations Density 0.012%

    No Known Activations