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. 98223
    Prev
    Next
    INDEX
    Explanations

    boot repair

    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
    vate
    -0.08
    税込
    -0.07
    rades
    -0.07
     وكانت
    -0.07
    720
    -0.07
    (net
    -0.07
    724
    -0.07
    .loads
    -0.07
    adu
    -0.07
    원을
    -0.07
    POSITIVE LOGITS
     falta
    0.09
    absence
    0.08
    Й
    0.08
     recovering
    0.08
     بدون
    0.08
     lack
    0.08
    without
    0.08
     обс
    0.08
     façade
    0.08
    									↵
    0.07
    Activations Density 0.003%

    No Known Activations