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. 9231
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     stark
    -0.08
    ninger
    -0.08
     stev
    -0.08
     desenvolver
    -0.08
     extender
    -0.08
     grim
    -0.07
    сия
    -0.07
     superintendent
    -0.07
     SEP
    -0.07
    (SIG
    -0.07
    POSITIVE LOGITS
     Mort
    0.08
     Gilbert
    0.07
     Vinci
    0.07
    为什么
    0.07
     इसी
    0.07
    qqu
    0.07
     Pon
    0.07
     yank
    0.07
     koszt
    0.07
     궁
    0.07
    Activations Density 0.106%

    No Known Activations