© 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. 65033
    Prev
    Next
    INDEX
    Explanations

    History

    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
     toppings
    -0.10
     sesame
    -0.08
     ropa
    -0.08
     roupas
    -0.08
    兑换
    -0.08
     ath
    -0.08
     dona
    -0.08
     creatives
    -0.08
     cannabis
    -0.07
     ödeme
    -0.07
    POSITIVE LOGITS
     chronicles
    0.13
     chronological
    0.12
     chronology
    0.12
     recount
    0.12
     encycl
    0.11
     기록
    0.11
     narratives
    0.11
     Chronicles
    0.11
     biographies
    0.10
     racont
    0.10
    Activations Density 0.019%

    No Known Activations