© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112395
    Prev
    Next
    INDEX
    Explanations

    parentheses and addition

    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
     conservative
    -0.09
     respect
    -0.08
     converse
    -0.08
     com
    -0.08
     gla
    -0.07
    prech
    -0.07
     Conservative
    -0.07
     Bah
    -0.07
     buffet
    -0.07
    suggest
    -0.07
    POSITIVE LOGITS
     случаи
    0.09
    ոշ
    0.09
    Uso
    0.09
     მუშ
    0.09
    ուրջ
    0.09
    _BUSY
    0.08
    աշխ
    0.08
    itsumik
    0.08
     akili
    0.08
    րս
    0.08
    Activations Density 0.018%

    No Known Activations