© 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. 94978
    Prev
    Next
    INDEX
    Explanations

    analytics

    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
    arı
    -0.08
     Tic
    -0.08
     Toc
    -0.07
    größe
    -0.07
     удал
    -0.07
     Pork
    -0.07
    電
    -0.07
     między
    -0.07
     só
    -0.07
    ğun
    -0.07
    POSITIVE LOGITS
    指标
    0.08
     proactively
    0.08
     Platform
    0.08
    (bind
    0.08
    平台
    0.08
    .^
    0.08
     Geb
    0.07
    사이트
    0.07
     soar
    0.07
    -tech
    0.07
    Activations Density 0.008%

    No Known Activations