© 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. 24931
    Prev
    Next
    INDEX
    Explanations

    start

    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
    ੱਖ
    -0.08
     Royce
    -0.08
    sspiel
    -0.08
    ъя
    -0.08
     Finale
    -0.08
    項
    -0.08
    START
    -0.07
     PERF
    -0.07
    érieur
    -0.07
     rustic
    -0.07
    POSITIVE LOGITS
     sembl
    0.09
     читать
    0.08
    (()=>{↵
    0.08
    吃
    0.08
    anj
    0.08
     ngoku
    0.08
     lect
    0.07
    逐
    0.07
     petrol
    0.07
     получать
    0.07
    Activations Density 0.041%

    No Known Activations