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. 77266
    Prev
    Next
    INDEX
    Explanations

    steps in a process

    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
     Voyage
    -0.09
     stringent
    -0.08
     retailer
    -0.08
     sufferers
    -0.08
     heightened
    -0.08
     Approval
    -0.08
     Wilhelm
    -0.08
     Comparative
    -0.08
     يش
    -0.08
     призн
    -0.08
    POSITIVE LOGITS
    What's
    0.09
     magie
    0.09
    Longest
    0.09
     файлов
    0.09
     코드
    0.09
     executed
    0.08
    幕后
    0.08
     reused
    0.08
    ачем
    0.08
     passiert
    0.08
    Activations Density 0.011%

    No Known Activations