© 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. 95293
    Prev
    Next
    INDEX
    Explanations

    الذ

    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
     बना
    -0.08
    Deal
    -0.08
     fave
    -0.08
     freelance
    -0.08
     Rider
    -0.08
     Dodge
    -0.08
     Fav
    -0.08
    šu
    -0.08
    śred
    -0.07
    וצ
    -0.07
    POSITIVE LOGITS
     ال
    0.09
     antip
    0.08
     lob
    0.08
     è
    0.08
    Ml
    0.08
     antim
    0.08
     carp
    0.07
    وقت
    0.07
    ائح
    0.07
     ven
    0.07
    Activations Density 0.008%

    No Known Activations