© 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. 29527
    Prev
    Next
    INDEX
    Explanations

    C++ consteval keyword

    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
    ROOM
    -0.09
    thorn
    -0.08
    Thong
    -0.08
    Decorator
    -0.08
    gew
    -0.08
    case
    -0.08
     શુભ
    -0.08
    Benchmark
    -0.08
     bedacht
    -0.07
    Ngu
    -0.07
    POSITIVE LOGITS
     Kik
    0.08
    =set
    0.08
    字号
    0.08
    anar
    0.07
    uced
    0.07
     hears
    0.07
    阅
    0.07
     Nat
    0.07
     mamm
    0.07
     ele
    0.07
    Activations Density 0.000%

    No Known Activations