© 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. 71751
    Prev
    Next
    INDEX
    Explanations

    cohort

    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
     rote
    -0.08
    ↵↵ ↵↵
    -0.08
     boutique
    -0.07
    weil
    -0.07
     taşı
    -0.07
     amplification
    -0.07
    -0.07
     tempest
    -0.07
    곳
    -0.07
     Neural
    -0.06
    POSITIVE LOGITS
     Younger
    0.09
     cohorts
    0.09
     étaient
    0.09
     Nowadays
    0.09
     покол
    0.09
     socio
    0.09
     lagen
    0.08
     künftig
    0.08
     eras
    0.08
     générations
    0.08
    Activations Density 0.008%
    No Known Activations