© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54536
    Prev
    Next
    INDEX
    Explanations

    t

    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
    传统
    -0.07
    策
    -0.07
    anato
    -0.07
     nesting
    -0.07
     tradi
    -0.07
     trong
    -0.07
     trin
    -0.07
     feat
    -0.07
    ídu
    -0.07
     gland
    -0.07
    POSITIVE LOGITS
    _elapsed
    0.12
    Elapsed
    0.11
     суток
    0.11
    elapsed
    0.11
    .time
    0.10
     elapsed
    0.10
    .elapsed
    0.10
     秒
    0.10
    Seconds
    0.10
    =time
    0.10
    Activations Density 0.018%

    No Known Activations