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

    Neuronpedia

    APICircuit 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. 11988
    Prev
    Next
    INDEX
    Explanations

    front

    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
    ɑ
    -0.09
    ững
    -0.08
     nouvelles
    -0.08
     modifies
    -0.07
    ildi
    -0.07
     Champion
    -0.07
     Rodr
    -0.07
    ences
    -0.07
    扎
    -0.07
     Wilder
    -0.07
    POSITIVE LOGITS
    -facing
    0.09
     prett
    0.09
     автоматически
    0.09
     hemisphere
    0.08
     ఉంట
    0.08
     diálogo
    0.08
     selfies
    0.08
     থেকেই
    0.08
     всему
    0.08
     камеры
    0.08
    Activations Density 0.001%

    No Known Activations