© 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. 23-RESID-POST-AA
    11. 48057
    Prev
    Next
    INDEX
    Explanations

    monasteries

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
    ייחס
    -0.08
    人民网
    -0.07
     métall
    -0.07
    �
    -0.07
     divider
    -0.07
     playlists
    -0.07
     sprinkler
    -0.07
     rollover
    -0.07
    פורט
    -0.07
    POSITIVE LOGITS
     monastery
    0.20
     monks
    0.19
     monaster
    0.19
     mon
    0.18
     мона
    0.17
    尼姑
    0.17
     convent
    0.17
     abb
    0.16
     Abbey
    0.16
     monk
    0.16
    Activations Density 0.023%

    No Known Activations