© 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. 15-RESID-POST-AA
    11. 16280
    Prev
    Next
    INDEX
    Explanations

    backslashes and semicolons

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     burdens
    -0.08
     \"%
    -0.08
     \"
    -0.08
    niv
    -0.08
    ലയാള
    -0.08
     differs
    -0.08
     hasn
    -0.07
     (“
    -0.07
     recorr
    -0.07
    ity
    -0.07
    POSITIVE LOGITS
    　
    0.08
     ।
    0.08
    ။
    0.08
     فإن
    0.08
    ansom
    0.08
    ）。
    0.08
    ៖
    0.07
    ៈ
    0.07
    0.07
    ।
    0.07
    Activations Density 0.013%

    No Known Activations