© 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. 23-RESID-POST-AA
    11. 52292
    Prev
    Next
    INDEX
    Explanations

    scientific measurements with numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     פּר
    -0.08
    ाइज
    -0.08
     artista
    -0.07
    ော
    -0.07
     Proc
    -0.07
     yp
    -0.07
    agia
    -0.07
    ুল
    -0.07
    pro
    -0.07
     Str
    -0.07
    POSITIVE LOGITS
    -co
    0.08
     Interstate
    0.07
    万
    0.07
    aco
    0.07
    萬
    0.07
    美国
    0.07
    USA
    0.07
     万
    0.07
    usa
    0.07
     Amerikaanse
    0.07
    Activations Density 0.029%

    No Known Activations