Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130966
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kla
    -0.09
    Uuid
    -0.08
    â
    -0.08
    checksum
    -0.08
     Plata
    -0.08
     accents
    -0.08
    Checksum
    -0.07
     Macs
    -0.07
     aleg
    -0.07
    eping
    -0.07
    POSITIVE LOGITS
     ദ
    0.09
    次数
    0.09
     вызывает
    0.08
     чат
    0.08
    沙
    0.08
    concat
    0.08
     та
    0.08
     funcionamiento
    0.08
     arth
    0.07
     вызвать
    0.07
    Activations Density 0.075%

    No Known Activations