© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110692
    Prev
    Next
    INDEX
    Explanations

    contradiction

    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
    ollo
    -0.08
    ಾವಣ
    -0.08
     되
    -0.08
     высокого
    -0.08
     Titles
    -0.08
     visant
    -0.07
    boss
    -0.07
     высокий
    -0.07
     하는
    -0.07
     personnal
    -0.07
    POSITIVE LOGITS
     geen
    0.09
     intrins
    0.09
    无需
    0.08
     mime
    0.08
     cannot
    0.08
     invented
    0.08
     intrinsic
    0.08
    却
    0.08
     счет
    0.08
     inherently
    0.08
    Activations Density 0.003%

    No Known Activations