© 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. 71663
    Prev
    Next
    INDEX
    Explanations

    Spreading in area

    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
     وبر
    -0.08
     sorry
    -0.08
     caixa
    -0.08
    -camera
    -0.08
     cca
    -0.08
     ساتھ
    -0.07
     together
    -0.07
     vorher
    -0.07
     hamwe
    -0.07
     modelo
    -0.07
    POSITIVE LOGITS
     rộng
    0.12
    広
    0.10
    广
    0.10
     വ്യാപ
    0.09
    廣
    0.09
     распрост
    0.09
     diverse
    0.08
    群众
    0.08
     širo
    0.08
     widely
    0.08
    Activations Density 0.092%

    No Known Activations