© 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. 44777
    Prev
    Next
    INDEX
    Explanations

    economics/academics

    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
     légèrement
    -0.08
    kog
    -0.08
     dicha
    -0.08
     kami
    -0.08
     भारी
    -0.07
     लगता
    -0.07
     إقامة
    -0.07
     सीधे
    -0.07
     wsk
    -0.07
     काफी
    -0.07
    POSITIVE LOGITS
     vs
    0.12
     وكيف
    0.10
     beginners
    0.09
    简介
    0.09
     basics
    0.09
    练
    0.09
     etiquette
    0.09
    的重要
    0.09
    ачем
    0.09
    是什么意思
    0.09
    Activations Density 0.142%

    No Known Activations