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. 56058
    Prev
    Next
    INDEX
    Explanations

    news events business

    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
     tenure
    -0.07
    Transferred
    -0.07
    Trail
    -0.07
     Rush
    -0.07
     zelfs
    -0.07
    config
    -0.07
    -ten
    -0.07
    Ten
    -0.07
    -0.07
    了解
    -0.07
    POSITIVE LOGITS
     zugleich
    0.09
    judice
    0.09
     ನಡುವ
    0.09
     Dys
    0.08
     തമ്മ
    0.08
    \Collection
    0.08
     together
    0.08
     combo
    0.07
     bya
    0.07
     autor
    0.07
    Activations Density 0.223%

    No Known Activations