© 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. 19-RESID-POST-AA
    11. 18002
    Prev
    Next
    INDEX
    Explanations

    Formula

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     formula
    -0.11
     formulas
    -0.11
    _formula
    -0.09
    formula
    -0.08
     confirm
    -0.08
     algorithms
    -0.08
     confirmar
    -0.08
     confirmed
    -0.08
     confirmer
    -0.08
     सूत्र
    -0.08
    POSITIVE LOGITS
     One
    0.09
    -One
    0.09
    -one
    0.09
     адзін
    0.09
    ाउनु
    0.08
     jedan
    0.08
    One
    0.08
    .bank
    0.08
     јед
    0.08
     ụgbọ
    0.08
    Activations Density 0.006%

    No Known Activations