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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 13174
    Prev
    Next
    INDEX
    Explanations

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rawa
    -0.08
    ";
↵
    -0.08
    _reserved
    -0.08
    adara
    -0.08
    adata
    -0.07
    /url
    -0.07
     Webinar
    -0.07
     رج
    -0.07
     ذر
    -0.07
    ";
↵
↵
    -0.07
    POSITIVE LOGITS
    wiz
    0.08
    essment
    0.07
    arz
    0.07
    ikelihood
    0.07
     calidad
    0.07
     lint
    0.07
     Morning
    0.07
     asil
    0.07
    ταν
    0.07
     Fran
    0.07
    Activations Density 0.000%

    No Known Activations