© 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. 11-RESID-POST-AA
    11. 99149
    Prev
    Next
    INDEX
    Explanations

    trigonometry angles

    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
    稿
    -0.09
     unprecedented
    -0.08
    precedented
    -0.08
     billions
    -0.07
     яго
    -0.07
     beacon
    -0.07
     аж
    -0.07
    913
    -0.07
    'impression
    -0.07
    ifar
    -0.07
    POSITIVE LOGITS
     आतंक
    0.09
     Vin
    0.08
     clog
    0.08
     Koz
    0.08
     Pud
    0.08
     zdrav
    0.07
     carp
    0.07
     pesc
    0.07
     culin
    0.07
     sabendo
    0.07
    Activations Density 0.021%

    No Known Activations