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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 102861
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    .attrs
    -0.08
     Ax
    -0.08
    .href
    -0.08
    属性
    -0.07
    .arr
    -0.07
    .keras
    -0.07
    .resources
    -0.07
     Jared
    -0.07
    深
    -0.07
    .pool
    -0.07
    POSITIVE LOGITS
     poh
    0.08
     toegepast
    0.08
    uck
    0.08
     Hadd
    0.07
     CPM
    0.07
     Posting
    0.07
    hic
    0.07
    anhia
    0.07
     підтрим
    0.07
    pem
    0.07
    Activations Density 0.014%

    No Known Activations