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. 111748
    Prev
    Next
    INDEX
    Explanations

    probability

    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
     elasticity
    -0.08
     elektric
    -0.08
    TRAIN
    -0.08
     delegate
    -0.08
     crank
    -0.08
     เ
    -0.07
     deleg
    -0.07
     mở
    -0.07
     HID
    -0.07
     Electricity
    -0.07
    POSITIVE LOGITS
    .random
    0.12
     Random
    0.12
    随机
    0.12
    Random
    0.12
    _random
    0.11
     random
    0.11
    .Random
    0.11
    (random
    0.10
    random
    0.10
     probabil
    0.10
    Activations Density 0.016%

    No Known Activations