Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 112742
    Prev
    Next
    INDEX
    Explanations

    code and stack expressions

    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
    .Transactional
    -0.08
     mass
    -0.07
     masses
    -0.07
     ring
    -0.07
    JPEG
    -0.07
     remains
    -0.07
    लक
    -0.07
    mass
    -0.07
     whereby
    -0.07
     MASS
    -0.07
    POSITIVE LOGITS
     recomienda
    0.08
    ्यम
    0.08
     ocio
    0.08
    llo
    0.08
     Seni
    0.08
     recomendado
    0.08
    نن
    0.08
    (attrs
    0.08
    ന്തര
    0.08
     horas
    0.08
    Activations Density 0.001%

    No Known Activations