© 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. 52053
    Prev
    Next
    INDEX
    Explanations

    з

    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
    annu
    -0.09
    keet
    -0.08
    udan
    -0.08
     Evangel
    -0.08
     Identification
    -0.08
     Arthur
    -0.08
     autograph
    -0.07
     solos
    -0.07
     dits
    -0.07
    zame
    -0.07
    POSITIVE LOGITS
    гляд
    0.12
    гля
    0.11
    ять
    0.09
    рос
    0.08
    GLISH
    0.07
    C
    0.07
    781
    0.07
     wind
    0.07
    .not
    0.07
     cir
    0.07
    Activations Density 0.000%

    No Known Activations