Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11687
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     peso
    -0.09
    _WEIGHT
    -0.08
    ือง
    -0.08
     hechos
    -0.07
    .NON
    -0.07
     lauf
    -0.07
     응
    -0.07
     કામ
    -0.07
    peso
    -0.07
     Peso
    -0.07
    POSITIVE LOGITS
     পৌঁ
    0.10
     iterations
    0.10
    Iterations
    0.10
     reach
    0.10
     পর্যন্ত
    0.09
    Reached
    0.09
    Después
    0.09
    После
    0.09
     reached
    0.09
    _iterations
    0.09
    Activations Density 0.036%

    No Known Activations