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. 120371
    Prev
    Next
    INDEX
    Explanations

    geometric lines

    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
    Authorize
    -0.07
     imperial
    -0.07
     eenvoudige
    -0.07
    хат
    -0.07
    英语
    -0.07
     modell
    -0.07
     прав
    -0.07
     Engelse
    -0.07
    _lock
    -0.07
     Axel
    -0.07
    POSITIVE LOGITS
    ansa
    0.10
     Ligne
    0.09
     դրա
    0.08
    iciente
    0.08
    čnosti
    0.08
    คู่
    0.08
     Прод
    0.08
     Semin
    0.08
     նրա
    0.08
     continu
    0.08
    Activations Density 0.032%

    No Known Activations