© 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. 19-RESID-POST-AA
    11. 18057
    Prev
    Next
    INDEX
    Explanations

    Cel

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .unsplash
    -0.09
    -0.08
     חמ
    -0.08
    -нибудь
    -0.08
     Donnerstag
    -0.07
     '
    -0.07
    чики
    -0.07
     محف
    -0.07
    करण
    -0.07
     تريد
    -0.07
    POSITIVE LOGITS
    estial
    0.15
    plug
    0.11
    so
    0.11
    este
    0.11
    cius
    0.10
    estin
    0.10
    les
    0.10
    ular
    0.10
    Plug
    0.10
    ెస్ట
    0.10
    Activations Density 0.008%
    No Known Activations