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. 60881
    Prev
    Next
    INDEX
    Explanations

    go ahead, permission

    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
    sw
    -0.08
    hr
    -0.07
     vän
    -0.07
    otra
    -0.07
     į
    -0.07
    役
    -0.07
    -0.07
    redi
    -0.07
     Hair
    -0.07
    امی
    -0.07
    POSITIVE LOGITS
     whatever
    0.10
     gerust
    0.09
     Whatever
    0.09
    Whatever
    0.09
    吧
    0.09
     plum
    0.09
    whatever
    0.08
    放心
    0.08
     ruhig
    0.08
     wherever
    0.08
    Activations Density 0.035%

    No Known Activations