© 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. 735
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     vip
    -0.09
    ního
    -0.08
    vip
    -0.08
     saints
    -0.08
    halo
    -0.08
     etiquette
    -0.07
    еров
    -0.07
     seda
    -0.07
     فرآ
    -0.07
    checkbox
    -0.07
    POSITIVE LOGITS
    是多少
    0.08
     Trick
    0.08
    ansas
    0.08
    Either
    0.08
     Parameter
    0.08
     Override
    0.07
     Choice
    0.07
    (j
    0.07
     Answer
    0.07
     المطل
    0.07
    Activations Density 0.058%

    No Known Activations