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. 76525
    Prev
    Next
    INDEX
    Explanations

    math

    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
     fourteen
    -0.08
    .forms
    -0.08
     kadar
    -0.08
     Eleven
    -0.07
    cind
    -0.07
    _elem
    -0.07
    Elem
    -0.07
    .optional
    -0.07
     Fifty
    -0.07
     మా
    -0.07
    POSITIVE LOGITS
    :left
    0.09
     runaway
    0.09
    ,left
    0.09
     direction
    0.08
    /weather
    0.08
     左
    0.08
    (left
    0.08
     esquerda
    0.08
     Polynomial
    0.08
     left
    0.08
    Activations Density 0.010%

    No Known Activations