Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 46065
    Prev
    Next
    INDEX
    Explanations

    is

    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
    vasive
    -0.09
     etabl
    -0.08
    *)(
    -0.08
    елик
    -0.07
     insightful
    -0.07
    -muted
    -0.07
     representative
    -0.07
    енной
    -0.07
    ARO
    -0.07
     subscription
    -0.07
    POSITIVE LOGITS
    markup
    0.08
     documentación
    0.07
     markup
    0.07
     Förder
    0.07
     Kish
    0.07
    /general
    0.07
    四六
    0.07
     gotas
    0.07
     kile
    0.07
     quedar
    0.07
    Activations Density 0.003%

    No Known Activations