© 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. 79391
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    .vars
    -0.09
    .expr
    -0.08
    どう
    -0.08
    _expr
    -0.07
     trasc
    -0.07
    .symmetric
    -0.07
    以内
    -0.07
    表达
    -0.07
     módulos
    -0.07
     וש
    -0.07
    POSITIVE LOGITS
     Griechen
    0.08
     অন্যতম
    0.08
    ارة
    0.08
     suele
    0.07
    368
    0.07
     Harvard
    0.07
     പോല
    0.07
    ارات
    0.07
     Greeks
    0.07
    uss
    0.07
    Activations Density 0.112%

    No Known Activations