© 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. 52158
    Prev
    Next
    INDEX
    Explanations

    Teenagers and stories

    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
    פקיד
    -0.09
     Michelin
    -0.08
    משך
    -0.08
    нути
    -0.08
    משיך
    -0.08
     шмат
    -0.08
     murder
    -0.08
     dinner
    -0.08
     משפ
    -0.08
     cure
    -0.08
    POSITIVE LOGITS
    -radio
    0.10
     adolescente
    0.09
    -a
    0.09
    -average
    0.08
    -year
    0.08
    -Line
    0.08
    -songwriter
    0.08
    .radio
    0.08
     Uph
    0.08
    -energy
    0.08
    Activations Density 0.005%

    No Known Activations