© 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. 23-RESID-POST-AA
    11. 97359
    Prev
    Next
    INDEX
    Explanations

    Large number calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pondering
    -0.08
     meilleurs
    -0.08
    uation
    -0.08
    jak
    -0.08
    ้วย
    -0.07
     domen
    -0.07
     Ravens
    -0.07
     voluptatem
    -0.07
    wier
    -0.07
    upaten
    -0.07
    POSITIVE LOGITS
    741
    0.09
     appeal
    0.08
     Appeal
    0.08
     vært
    0.08
    Ime
    0.07
     geproduceerd
    0.07
     작성
    0.07
     장
    0.07
    /dr
    0.07
     इल
    0.07
    Activations Density 0.001%

    No Known Activations