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. 60791
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     wiz
    -0.07
    (open
    -0.07
    (stats
    -0.07
    'nın
    -0.07
     Sitz
    -0.07
     Diploma
    -0.07
    歩
    -0.07
     huur
    -0.07
    :CGRect
    -0.07
     suggest
    -0.07
    POSITIVE LOGITS
     appearing
    0.08
     ecommerce
    0.08
     prévention
    0.08
     lançado
    0.08
     unor
    0.08
     lançamento
    0.08
     aparece
    0.08
     eus
    0.08
     lanç
    0.08
    Pairs
    0.08
    Activations Density 0.015%

    No Known Activations