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. 12180
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Frequently
    -0.08
    _verified
    -0.08
     скач
    -0.08
     frequently
    -0.08
    -author
    -0.07
     knocked
    -0.07
     nickel
    -0.07
    .acquire
    -0.07
     geeks
    -0.07
     mais
    -0.07
    POSITIVE LOGITS
    σμα
    0.09
     객
    0.08
    σματα
    0.08
    【
    0.08
     keywords
    0.08
    ledes
    0.08
    ---↵
    0.07
     letra
    0.07
    יכ
    0.07
    keywords
    0.07
    Activations Density 0.006%

    No Known Activations