© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99884
    Prev
    Next
    INDEX
    Explanations

    Random text

    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
     ნების
    -0.11
     კანდ
    -0.11
     ონ
    -0.11
    აოდენ
    -0.11
    �ედავად
    -0.10
     სად
    -0.10
     ხომ
    -0.10
    �უნ
    -0.10
    ცია
    -0.10
     ғына
    -0.10
    POSITIVE LOGITS
    ību
    0.08
    î
    0.08
    іт
    0.08
     bind
    0.08
    _CTRL
    0.07
    784
    0.07
    225
    0.07
     agile
    0.07
    724
    0.07
    441
    0.07
    Activations Density 2.429%

    No Known Activations