© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21191
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    /or
    -0.09
    (that
    -0.09
     that
    -0.09
     belonged
    -0.08
     with
    -0.08
     entirely
    -0.08
     belongs
    -0.08
    '=
    -0.07
     fully
    -0.07
     completely
    -0.07
    POSITIVE LOGITS
     പ്രധാന
    0.10
     ಮುಖ್ಯ
    0.10
     أهم
    0.10
    middleware
    0.10
     중요한
    0.09
     principais
    0.09
    Layouts
    0.09
    Locales
    0.09
    .middleware
    0.09
     principales
    0.09
    Activations Density 0.003%

    No Known Activations