© 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. 109949
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     espalda
    -0.09
    /fw
    -0.09
     autograph
    -0.09
    ='<
    -0.08
     Airline
    -0.08
     automate
    -0.08
    外国
    -0.07
    (wallet
    -0.07
     sentirse
    -0.07
     exemption
    -0.07
    POSITIVE LOGITS
     Combining
    0.10
     mixtures
    0.10
    ombi
    0.09
    .combine
    0.09
     hue
    0.09
    _mix
    0.09
    addition
    0.08
     HSV
    0.08
     synergy
    0.08
     بنیادی
    0.08
    Activations Density 0.012%

    No Known Activations