© 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. 11-RESID-POST-AA
    11. 25069
    Prev
    Next
    INDEX
    Explanations

    contents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lev
    -0.07
     doon
    -0.07
     Valor
    -0.07
     Aire
    -0.07
     É
    -0.07
     Discipline
    -0.07
     Alien
    -0.07
    .ep
    -0.07
     Flex
    -0.07
     DHA
    -0.07
    POSITIVE LOGITS
    μένη
    0.09
     hiçbir
    0.09
     succession
    0.09
     Sieger
    0.08
     plaus
    0.08
     plausible
    0.08
     {[
    0.08
    isessä
    0.08
     бл
    0.08
    밍
    0.08
    Activations Density 0.001%

    No Known Activations