© 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. 71440
    Prev
    Next
    INDEX
    Explanations

    international law customs

    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
     c
    -0.07
     dopamine
    -0.07
    agnitude
    -0.07
     الترك
    -0.07
     పూర్తి
    -0.07
     prescription
    -0.06
    嬉
    -0.06
     q
    -0.06
     characterization
    -0.06
    ‌کن
    -0.06
    POSITIVE LOGITS
     traditions
    0.10
     folklore
    0.09
     byl
    0.09
     treaties
    0.09
     deeds
    0.09
    :I
    0.09
     natürliche
    0.09
     Episc
    0.09
     naturais
    0.09
    .DEFAULT
    0.09
    Activations Density 0.008%

    No Known Activations