© 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. 45537
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts

    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
    омин
    -0.10
    ланған
    -0.08
     homosexual
    -0.08
    ирақ
    -0.08
     modalités
    -0.08
    不要
    -0.08
     міндет
    -0.08
    омина
    -0.08
    हो
    -0.08
     yleensä
    -0.08
    POSITIVE LOGITS
     merely
    0.10
     mere
    0.09
     مجرد
    0.09
     disparate
    0.09
     superficial
    0.08
     fleeting
    0.08
     mundane
    0.08
     bland
    0.08
     toev
    0.08
     obscure
    0.08
    Activations Density 0.115%

    No Known Activations