© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7737
    Prev
    Next
    INDEX
    Explanations

    Urgent need to defecate

    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
    ાઇટ
    -0.08
    grat
    -0.08
     Removed
    -0.08
     garnered
    -0.08
    ાયેલ
    -0.08
     Sveriges
    -0.08
    ڄ
    -0.07
     harvested
    -0.07
    mata
    -0.07
     retrieved
    -0.07
    POSITIVE LOGITS
    厕所
    0.11
     bathroom
    0.11
     bathrooms
    0.10
     toilettes
    0.10
    Bathroom
    0.09
     toilets
    0.09
     société
    0.09
     délais
    0.09
    厕
    0.08
     Bathroom
    0.08
    Activations Density 0.015%

    No Known Activations