© 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. 31333
    Prev
    Next
    INDEX
    Explanations

    number theory

    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
     trud
    -0.09
    noun
    -0.09
    irebase
    -0.09
     mote
    -0.08
    อะ
    -0.08
     zow
    -0.08
     retirees
    -0.08
     moeilijk
    -0.08
    	boost
    -0.08
    무
    -0.08
    POSITIVE LOGITS
     لتن
    0.08
     لس
    0.08
    :test
    0.08
     لت
    0.07
    .Meta
    0.07
     месяца
    0.07
    iann
    0.07
    .At
    0.07
    %s
    0.07
     علامة
    0.07
    Activations Density 0.017%

    No Known Activations