© 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. 71526
    Prev
    Next
    INDEX
    Explanations

    distinct

    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
    Negative Logits
     lep
    -0.09
    )`↵
    -0.07
     Cura
    -0.07
     Har
    -0.07
     Hom
    -0.07
     Colin
    -0.07
     ingin
    -0.07
     becomes
    -0.07
     তখন
    -0.06
     instanceof
    -0.06
    POSITIVE LOGITS
     variations
    0.09
    variation
    0.09
    颖
    0.08
     вари
    0.08
     vegetal
    0.08
     substantive
    0.08
     anatomical
    0.08
     вариантов
    0.08
    特色
    0.08
     palate
    0.08
    Activations Density 0.002%

    No Known Activations