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. 12031
    Prev
    Next
    INDEX
    Explanations

    randint

    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
     initializing
    -0.08
    .Mock
    -0.08
    ач
    -0.08
    мач
    -0.07
    .Person
    -0.07
    .Det
    -0.07
    Dies
    -0.07
    stanz
    -0.07
    pendency
    -0.07
    stelle
    -0.07
    POSITIVE LOGITS
     BETWEEN
    0.10
    _between
    0.10
    Inclusive
    0.10
     between
    0.09
     Inclusive
    0.09
     بين
    0.09
     inclusive
    0.09
     Between
    0.08
    Between
    0.08
     пределах
    0.08
    Activations Density 0.002%

    No Known Activations