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. 76264
    Prev
    Next
    INDEX
    Explanations

    significantly and math problems

    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
    ];↵↵
    -0.09
     DPI
    -0.08
    ic
    -0.07
    __
    -0.07
    -0.07
     interest
    -0.07
    false
    -0.07
    P
    -0.07
    Il
    -0.07
     SUV
    -0.07
    POSITIVE LOGITS
    нете
    0.10
     gamblers
    0.09
    มา
    0.08
     Favourite
    0.08
     واست
    0.08
     summar
    0.08
    ніх
    0.08
    астроф
    0.08
    ехника
    0.08
    яя
    0.08
    Activations Density 0.000%

    No Known Activations