© 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. 898
    Prev
    Next
    INDEX
    Explanations

    then

    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
    ிக்கும்
    -0.07
     ביותר
    -0.07
     منها
    -0.07
     эффективность
    -0.07
     ધર
    -0.07
     kraj
    -0.07
    цел
    -0.07
     إلا
    -0.07
    육
    -0.07
    نك
    -0.07
    POSITIVE LOGITS
    寝
    0.09
     --------
    0.08
    ████
    0.08
    ありません
    0.08
    ots
    0.08
    になります
    0.08
     ****************
    0.08
     മുതൽ
    0.08
    ward
    0.08
    一步
    0.07
    Activations Density 0.064%

    No Known Activations