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. 45003
    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
     Pic
    -0.08
     //@
    -0.08
    投入
    -0.07
     rugged
    -0.07
    adi
    -0.07
     fel
    -0.07
     skies
    -0.07
    Oak
    -0.07
    rado
    -0.07
     Ainda
    -0.07
    POSITIVE LOGITS
     Meghan
    0.09
     organically
    0.08
     ""↵↵
    0.08
     ''↵↵
    0.08
     {};↵↵
    0.08
     بہ
    0.08
     paka
    0.08
     кең
    0.08
     برو
    0.08
     موس
    0.08
    Activations Density 0.003%

    No Known Activations