© 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. 15-RESID-POST-AA
    11. 16517
    Prev
    Next
    INDEX
    Explanations

    empathy and compassion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     국내
    -0.09
     bd
    -0.08
     Worst
    -0.08
     전국
    -0.08
     ಪೂ
    -0.08
     운영
    -0.08
    quared
    -0.08
    _Static
    -0.08
    -ie
    -0.08
     Dysfunction
    -0.07
    POSITIVE LOGITS
     respectful
    0.10
     compassion
    0.10
     compassionate
    0.08
    尊
    0.08
     amazed
    0.08
     enchanted
    0.08
     especies
    0.08
     respe
    0.08
    Respect
    0.08
     empath
    0.08
    Activations Density 0.027%

    No Known Activations