© 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. 52028
    Prev
    Next
    INDEX
    Explanations

    Euclidean Algorithm

    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
     marketed
    -0.09
     افراد
    -0.09
     hoʻon
    -0.09
     لجميع
    -0.09
    _JSON
    -0.08
    ofanirwa
    -0.08
    -sensitive
    -0.08
     aufblasen
    -0.08
    יצוב
    -0.08
     colectiva
    -0.08
    POSITIVE LOGITS
     gcd
    0.20
     remainder
    0.18
     Eu
    0.12
     mod
    0.12
     step
    0.12
     recurse
    0.12
     previous
    0.12
     остат
    0.12
     steps
    0.12
     restos
    0.11
    Activations Density 0.037%

    No Known Activations