© 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. 19-RESID-POST-AA
    11. 102579
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     unwavering
    -0.11
     steadfast
    -0.10
    illusion
    -0.09
    坚定
    -0.08
     희
    -0.08
     왜
    -0.08
    soe
    -0.08
     incred
    -0.08
     solace
    -0.08
     beliefs
    -0.08
    POSITIVE LOGITS
     +
    0.09
    .↵↵
    0.08
    .
    0.08
     allows
    0.08
    ↵
    0.08
    ，需要
    0.08
     ->
    0.08
    >
    0.07
    لف
    0.07
     Mbps
    0.07
    Activations Density 0.025%

    No Known Activations