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. 117419
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    آ
    -0.08
    Что
    -0.08
    على
    -0.08
     Что
    -0.08
     żeby
    -0.07
     DU
    -0.07
    โปร
    -0.07
    至
    -0.07
    分钟
    -0.07
    (enabled
    -0.07
    POSITIVE LOGITS
     Sér
    0.08
    .to
    0.07
     Valentin
    0.07
    dirname
    0.07
    Mono
    0.07
     wb
    0.07
    .event
    0.07
    herited
    0.07
    Inverse
    0.07
    .Completed
    0.07
    Activations Density 0.047%

    No Known Activations