© 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. 71566
    Prev
    Next
    INDEX
    Explanations

    says, written, read

    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
     actresses
    -0.08
    ittura
    -0.07
    cemia
    -0.07
     unnecessary
    -0.07
    /(?
    -0.07
     picky
    -0.07
     oldu
    -0.07
    streams
    -0.07
    poses
    -0.07
     neurological
    -0.07
    POSITIVE LOGITS
     graffiti
    0.13
     printed
    0.12
     prominently
    0.12
     etched
    0.11
    printed
    0.11
     engraved
    0.11
     embroidered
    0.10
    Printed
    0.10
     над
    0.10
     displayed
    0.10
    Activations Density 0.116%

    No Known Activations