© 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. 95324
    Prev
    Next
    INDEX
    Explanations

    turn off notifications (or "Do-Not-Disturb")

    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
     étr
    -0.09
     толщ
    -0.07
     allt
    -0.07
    antwoord
    -0.07
     Trag
    -0.07
     stappen
    -0.07
     दृष्ट
    -0.07
     uspe
    -0.07
     البول
    -0.07
     informal
    -0.07
    POSITIVE LOGITS
    amed
    0.10
     selama
    0.09
     während
    0.08
     Scheduled
    0.08
     disruptions
    0.08
     během
    0.08
    iché
    0.08
     USART
    0.08
    凌晨
    0.07
     ночью
    0.07
    Activations Density 0.001%

    No Known Activations