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. 43395
    Prev
    Next
    INDEX
    Explanations

    Empathy

    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
     планы
    -0.08
     direitos
    -0.08
     યોજના
    -0.08
    archy
    -0.08
     योजना
    -0.08
     Plans
    -0.07
     Kings
    -0.07
     ṣ
    -0.07
    엄
    -0.07
    _COLUMNS
    -0.07
    POSITIVE LOGITS
     empathy
    0.12
     empat
    0.11
     empath
    0.11
    共享
    0.11
     contag
    0.11
     contagious
    0.10
     sympathy
    0.10
     shared
    0.10
    感染
    0.10
    分享
    0.09
    Activations Density 0.012%

    No Known Activations