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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99217
    Prev
    Next
    INDEX
    Explanations

    love and romance

    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
     origins
    -0.08
     ilu
    -0.08
    ต้น
    -0.08
     synonyms
    -0.07
    Origins
    -0.07
     við
    -0.07
     aanb
    -0.07
     kg
    -0.07
     الطب
    -0.07
    .beh
    -0.07
    POSITIVE LOGITS
     στε
    0.08
     promet
    0.08
     promete
    0.08
    候
    0.08
    pros
    0.08
     роб
    0.08
     Polaris
    0.08
    Voxel
    0.08
     aspiring
    0.08
     AUX
    0.08
    Activations Density 0.050%

    No Known Activations