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. 112897
    Prev
    Next
    INDEX
    Explanations

    voltage suppression diodes

    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
     Inbox
    -0.09
    ි
    -0.08
    hear
    -0.08
     ինտ
    -0.08
     Ø
    -0.08
    Ø
    -0.08
    ongo
    -0.08
     böyük
    -0.08
    රි
    -0.08
     intégrer
    -0.08
    POSITIVE LOGITS
    िका
    0.08
    ांची
    0.08
     corona
    0.08
     carbide
    0.08
    击
    0.08
    Vendor
    0.08
    Defines
    0.07
    들의
    0.07
    Voltage
    0.07
     afflicted
    0.07
    Activations Density 0.002%

    No Known Activations