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. 120358
    Prev
    Next
    INDEX
    Explanations

    epsilon

    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
     Sud
    -0.08
     Mia
    -0.08
     Hir
    -0.07
    ತ್ತ
    -0.07
    48
    -0.07
     Sofia
    -0.07
     locations
    -0.07
     Lus
    -0.07
     hop
    -0.07
     monitoring
    -0.07
    POSITIVE LOGITS
     epsilon
    0.10
    ILON
    0.09
     eps
    0.09
     ε
    0.08
     చిన్న
    0.08
     નાના
    0.08
     leuc
    0.08
    epsilon
    0.07
     toetsen
    0.07
    psilon
    0.07
    Activations Density 0.004%

    No Known Activations