© 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. 52263
    Prev
    Next
    INDEX
    Explanations

    /

    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
     bwa
    -0.10
     strdup
    -0.10
     stb
    -0.09
     další
    -0.09
     psyche
    -0.09
     rya
    -0.09
    .stub
    -0.09
     setup
    -0.09
    ("").
    -0.08
    =="
    -0.08
    POSITIVE LOGITS
     fractions
    0.11
    illors
    0.11
    /icons
    0.11
    ollars
    0.11
    -thirds
    0.10
     divisions
    0.10
     inches
    0.10
     factions
    0.10
     ounces
    0.10
     Instructions
    0.10
    Activations Density 0.077%

    No Known Activations