© 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. 71492
    Prev
    Next
    INDEX
    Explanations

    file sharing

    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
    Not in Any Lists

    No Comments

    Negative Logits
     قوة
    -0.09
     Cardi
    -0.08
     गोली
    -0.08
     الضغط
    -0.08
     Stress
    -0.08
     efficacité
    -0.08
     effectiveness
    -0.08
     القوة
    -0.08
    .firebaseio
    -0.08
     покол
    -0.08
    POSITIVE LOGITS
    Sharing
    0.12
    共享
    0.11
     sharing
    0.11
    分享
    0.11
     공유
    0.11
     доступ
    0.11
     compartir
    0.11
     શેર
    0.11
     Sharing
    0.10
     toegankelijk
    0.10
    Activations Density 0.011%

    No Known Activations