© 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. 68503
    Prev
    Next
    INDEX
    Explanations

    First aid/CPR

    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
     പ്ര
    -0.08
     comercio
    -0.08
     sentimental
    -0.08
     παραγω
    -0.08
     பிரத
    -0.07
     அதிக
    -0.07
     கே
    -0.07
    出售
    -0.07
     கேட்ட
    -0.07
     ολο
    -0.07
    POSITIVE LOGITS
     painless
    0.09
     रक्त
    0.08
     pupils
    0.08
     руками
    0.08
     Hände
    0.08
     tactile
    0.08
     blood
    0.08
     Helic
    0.08
    ِي
    0.07
     Bones
    0.07
    Activations Density 0.008%

    No Known Activations