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. 65125
    Prev
    Next
    INDEX
    Explanations

    hermeneutics

    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
     tidur
    -0.08
     rn
    -0.08
    ंघ
    -0.08
    ke
    -0.08
    RAM
    -0.07
    375
    -0.07
    ERO
    -0.07
     pher
    -0.07
    ‌ده
    -0.07
    aksan
    -0.07
    POSITIVE LOGITS
     нел
    0.08
     spezi
    0.08
     classics
    0.08
     klasik
    0.08
     archaeological
    0.08
     gesam
    0.08
     govern
    0.08
     tradicional
    0.08
    ämä
    0.08
     tradition
    0.08
    Activations Density 0.001%

    No Known Activations