Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77180
    Prev
    Next
    INDEX
    Explanations

    …

    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
    ↵      ↵
    -0.08
    יש
    -0.08
    -liter
    -0.08
    મેન્ટ
    -0.08
     lel
    -0.08
    -doc
    -0.08
     perms
    -0.07
     emot
    -0.07
    .related
    -0.07
    apps
    -0.07
    POSITIVE LOGITS
     beard
    0.09
    眠
    0.08
     Пос
    0.08
    тика
    0.08
     cough
    0.08
     steadily
    0.07
     scalp
    0.07
     هل
    0.07
     तेज
    0.07
     tirelessly
    0.07
    Activations Density 0.007%

    No Known Activations