© 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. 26477
    Prev
    Next
    INDEX
    Explanations

    line

    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
     Bigger
    -0.09
    രോ
    -0.08
     �
    -0.08
    观看
    -0.08
     Electoral
    -0.07
     Coron
    -0.07
     Treaty
    -0.07
     Bulg
    -0.07
     Beaut
    -0.07
     watched
    -0.07
    POSITIVE LOGITS
     출시
    0.09
     пит
    0.09
     محصولات
    0.09
    сия
    0.08
    理念
    0.08
     PD
    0.08
     одежды
    0.08
     diversified
    0.08
    商品
    0.08
     продукции
    0.07
    Activations Density 0.017%

    No Known Activations