© 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. 96797
    Prev
    Next
    INDEX
    Explanations

    авт

    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
    yj
    -0.09
    (er
    -0.08
    ние
    -0.08
     Erie
    -0.08
    oes
    -0.08
    syon
    -0.08
    yf
    -0.08
    ysize
    -0.08
     би
    -0.08
    roong
    -0.08
    POSITIVE LOGITS
     సె
    0.10
    амат
    0.09
     ಸೆ
    0.09
    .\
    0.09
     முக
    0.08
    оснаб
    0.08
     സെ
    0.08
    оп
    0.08
    开
    0.08
    .del
    0.08
    Activations Density 0.001%

    No Known Activations