© 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. 19-RESID-POST-AA
    11. 102627
    Prev
    Next
    INDEX
    Explanations

    reducing overhead and latency

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.10
     of
    -0.09
    ed
    -0.09
     or
    -0.08
     their
    -0.08
     документы
    -0.08
     ('
    -0.08
    ly
    -0.08
    uestas
    -0.08
     the
    -0.08
    POSITIVE LOGITS
     부담
    0.12
     overhead
    0.12
     비용
    0.11
     horsepower
    0.11
    成本
    0.10
    效率
    0.10
     меньше
    0.09
     زیادی
    0.09
    费用
    0.09
     karịa
    0.09
    Activations Density 0.027%

    No Known Activations