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. 88136
    Prev
    Next
    INDEX
    Explanations

    or

    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
    lower
    -0.07
    proc
    -0.07
    Azure
    -0.07
     supervision
    -0.07
    ral
    -0.07
    <>();↵
    -0.07
    Tesla
    -0.07
    ***
    -0.07
     তুল
    -0.07
    <<
    -0.07
    POSITIVE LOGITS
     Realty
    0.09
     kayo
    0.09
     mañana
    0.09
     kunjalo
    0.09
     gum
    0.09
     gik
    0.08
     Lucy
    0.08
     말씀
    0.08
     cyo
    0.08
    قى
    0.08
    Activations Density 0.003%

    No Known Activations