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. 12837
    Prev
    Next
    INDEX
    Explanations

    imaginary axis

    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
     ז
    -0.08
    ั่น
    -0.08
    Although
    -0.07
    тифик
    -0.07
    ంలో
    -0.07
    nameof
    -0.07
    ificação
    -0.07
     ferment
    -0.07
    Not
    -0.07
     antibiotics
    -0.07
    POSITIVE LOGITS
     Glory
    0.08
    wek
    0.07
    ovia
    0.07
     Jumbo
    0.07
    .groups
    0.07
     cenas
    0.07
     mambo
    0.07
     chaise
    0.07
    ��
    0.07
     rien
    0.07
    Activations Density 0.003%

    No Known Activations