© 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. 510
    Prev
    Next
    INDEX
    Explanations

    buffer

    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
     Pup
    -0.07
     Trek
    -0.07
    -May
    -0.07
     Loved
    -0.07
     buddh
    -0.07
    خيص
    -0.07
     ист
    -0.07
    �
    -0.07
     Valid
    -0.07
     futur
    -0.07
    POSITIVE LOGITS
     against
    0.13
     Against
    0.12
    Against
    0.11
    against
    0.10
     ضد
    0.10
     stave
    0.08
     اجرای
    0.08
     સામે
    0.08
    隔
    0.08
    Corona
    0.08
    Activations Density 0.006%

    No Known Activations