© 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. 23-RESID-POST-AA
    11. 52225
    Prev
    Next
    INDEX
    Explanations

    contr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     conforme
    -0.09
     Visual
    -0.07
     Staat
    -0.07
    UTF
    -0.07
    中心
    -0.07
     Negara
    -0.07
     Silicon
    -0.07
     Groen
    -0.07
    Ν
    -0.07
    QUIRE
    -0.07
    POSITIVE LOGITS
    ad
    0.29
    asting
    0.28
    asts
    0.23
    asted
    0.21
    aseña
    0.20
    ary
    0.18
    ôle
    0.17
    adic
    0.16
    	ad
    0.16
    astes
    0.15
    Activations Density 0.003%

    No Known Activations