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. 15-RESID-POST-AA
    6. 19049
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Printable
    -0.08
    واف
    -0.08
    ){}↵
    -0.08
    Focusable
    -0.08
    Phone
    -0.08
     Sox
    -0.08
    )"↵
    -0.08
    Thirty
    -0.07
     દર
    -0.07
     दर
    -0.07
    POSITIVE LOGITS
    ikation
    0.08
     Kant
    0.08
     zufrieden
    0.08
    __;
    0.08
     excellence
    0.07
     Fried
    0.07
     cemetery
    0.07
    pflege
    0.07
     sicher
    0.07
    .pb
    0.07
    Activations Density 0.001%

    No Known Activations