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. 88106
    Prev
    Next
    INDEX
    Explanations

    Subject

    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
    ाश
    -0.08
    Mons
    -0.08
    ેગ
    -0.08
    શ્વ
    -0.08
     expectation
    -0.08
     upbringing
    -0.08
     يحصل
    -0.08
     понадоб
    -0.07
     боку
    -0.07
     الجزء
    -0.07
    POSITIVE LOGITS
     Confidential
    0.08
    03
    0.08
    С
    0.07
     Pvt
    0.07
    20
    0.07
    039
    0.07
    0.07
     Wellness
    0.07
    two
    0.07
    (("
    0.07
    Activations Density 0.002%

    No Known Activations