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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99301
    Prev
    Next
    INDEX
    Explanations

    religion and scripture

    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
     socioeconomic
    -0.09
     पुरस्कार
    -0.08
     Emotional
    -0.08
     empathy
    -0.08
    /story
    -0.08
     palk
    -0.08
     refrigerated
    -0.08
     cooldown
    -0.08
    �
    -0.08
     statistically
    -0.08
    POSITIVE LOGITS
     doctr
    0.15
     Scriptures
    0.11
     doctrines
    0.11
     doctrine
    0.10
     disag
    0.10
     Euchar
    0.10
     disagreements
    0.10
     theological
    0.10
     disputed
    0.10
     agreed
    0.09
    Activations Density 0.038%

    No Known Activations