© 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. 18101
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    120
    -0.08
     calculations
    -0.08
    odynamics
    -0.07
    odynamic
    -0.07
     arbet
    -0.07
     calculation
    -0.07
     arbej
    -0.07
    .height
    -0.07
     энергии
    -0.07
     because
    -0.07
    POSITIVE LOGITS
     哪
    0.25
     Which
    0.25
    Which
    0.24
    Welche
    0.24
     Welche
    0.24
     hangi
    0.23
    哪些
    0.23
    Welke
    0.22
    哪个
    0.21
     hvilke
    0.21
    Activations Density 0.020%

    No Known Activations