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. 60056
    Prev
    Next
    INDEX
    Explanations

    class instances

    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
     recomend
    -0.08
    Recommendations
    -0.08
    .no
    -0.08
    ართ
    -0.08
     Crown
    -0.07
     recomendado
    -0.07
     vorgesch
    -0.07
     recommended
    -0.07
    Recommended
    -0.07
     chok
    -0.07
    POSITIVE LOGITS
    ाद
    0.10
     Apparently
    0.09
    ादन
    0.09
     आकर्ष
    0.08
     occurrence
    0.08
     apariencia
    0.08
     aparición
    0.08
     экземпля
    0.08
    INSTANCE
    0.08
    _instances
    0.08
    Activations Density 0.002%

    No Known Activations