© 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. 26591
    Prev
    Next
    INDEX
    Explanations

    stone

    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
    iat
    -0.08
     Bei
    -0.07
    sement
    -0.07
     пуст
    -0.07
     Tante
    -0.07
     empt
    -0.07
     empty
    -0.07
     GLOBAL
    -0.07
     asshole
    -0.07
     hunger
    -0.07
    POSITIVE LOGITS
    採
    0.09
     કરવામાં
    0.08
     construção
    0.08
     construcción
    0.08
     การ
    0.08
     craftsmanship
    0.08
     करण्यात
    0.08
    打造
    0.08
     públicas
    0.08
     brasileiras
    0.08
    Activations Density 0.010%

    No Known Activations