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. 11-RESID-POST-AA
    6. 30525
    Prev
    Next
    INDEX
    Explanations

    compound

    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
     Kirst
    -0.08
    hte
    -0.08
     Ler
    -0.07
    ),(
    -0.07
     Franklin
    -0.07
     aller
    -0.07
     desired
    -0.07
     انقلاب
    -0.07
     pioneering
    -0.07
    ..."↵↵
    -0.07
    POSITIVE LOGITS
     لأ
    0.08
    ുപ
    0.08
     Composite
    0.08
    假的
    0.08
     composite
    0.08
    /artificial
    0.08
    —for
    0.08
    Composite
    0.08
     comprised
    0.08
     பகுத
    0.08
    Activations Density 0.006%

    No Known Activations