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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102692
    Prev
    Next
    INDEX
    Explanations

    x

    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
    Not in Any Lists

    No Comments

    Negative Logits
    줄
    -0.08
     ballon
    -0.08
    stahl
    -0.07
     réflexion
    -0.07
     proche
    -0.07
     malformed
    -0.07
     the
    -0.07
     шу
    -0.07
     bogus
    -0.07
     导
    -0.07
    POSITIVE LOGITS
     acondicionado
    0.09
    .Random
    0.09
     Krankenhaus
    0.08
     extensively
    0.08
    _bins
    0.08
     winter
    0.08
    -language
    0.08
     institution
    0.08
    .LEFT
    0.08
     пределах
    0.08
    Activations Density 0.003%

    No Known Activations