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. 482
    Prev
    Next
    INDEX
    Explanations

    Separated information excerpt

    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
     quickest
    -0.08
     möglichst
    -0.08
     befindet
    -0.08
    ,但是
    -0.08
    PH
    -0.07
    BUT
    -0.07
     అని
    -0.07
     gewünschten
    -0.07
    .Try
    -0.07
     원하는
    -0.07
    POSITIVE LOGITS
     pioneering
    0.14
     pioneered
    0.12
     благодаря
    0.12
     Благодаря
    0.11
    贡献
    0.11
    推动
    0.10
     founding
    0.10
     groundbreaking
    0.10
     seminal
    0.10
     sayesinde
    0.10
    Activations Density 0.048%

    No Known Activations