© 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. 110033
    Prev
    Next
    INDEX
    Explanations

    Adapter

    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
     fewer
    -0.07
     وقت
    -0.07
    ubic
    -0.07
    yage
    -0.07
     nonlinear
    -0.07
     الاخت
    -0.07
     أحدث
    -0.07
     موعد
    -0.06
     Expo
    -0.06
    ↵
    -0.06
    POSITIVE LOGITS
    	style
    0.09
    .style
    0.09
    .Caption
    0.09
     Koe
    0.09
     francês
    0.08
     diction
    0.08
    .Style
    0.08
     financier
    0.08
     Kläger
    0.08
    .Controller
    0.08
    Activations Density 0.001%

    No Known Activations