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. 54206
    Prev
    Next
    INDEX
    Explanations

    #MeToo and sexual misconduct

    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
     [-]:
    -0.08
    reserve
    -0.07
     Grat
    -0.07
     -*
    -0.07
     результате
    -0.07
     каль
    -0.07
    OSP
    -0.07
     React
    -0.07
     Salzburg
    -0.07
     의해
    -0.07
    POSITIVE LOGITS
     allegations
    0.10
     alleged
    0.10
     workplace
    0.09
     harassment
    0.09
     alleging
    0.08
     alleges
    0.08
    职
    0.08
     Workplace
    0.08
    性
    0.08
     transgender
    0.08
    Activations Density 0.038%

    No Known Activations