© 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. 18051
    Prev
    Next
    INDEX
    Explanations

    代

    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
    .fly
    -0.08
    нуть
    -0.08
    ませ
    -0.08
    ирование
    -0.07
    .stack
    -0.07
    ")+"
    -0.07
     Callable
    -0.07
    ить
    -0.07
    ycz
    -0.07
    ления
    -0.07
    POSITIVE LOGITS
    efficient
    0.16
    eff
    0.15
    fficients
    0.14
    эффици
    0.13
    coeff
    0.13
    fficient
    0.12
    grees
    0.12
    ეფ
    0.11
     efic
    0.10
     eficiência
    0.10
    Activations Density 0.013%

    No Known Activations