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

    Neuronpedia

    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. 44650
    Prev
    Next
    INDEX
    Explanations

    student accommodations

    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
    902
    -0.08
     incorrectly
    -0.08
     elegantly
    -0.08
    544
    -0.08
     golf
    -0.08
     kvart
    -0.07
    563
    -0.07
    571
    -0.07
     vintage
    -0.07
     cubic
    -0.07
    POSITIVE LOGITS
     ವಿಷಯ
    0.08
     Unterricht
    0.08
     Anpass
    0.08
     verbal
    0.08
    ognitive
    0.08
     presentations
    0.08
     orale
    0.08
    课堂
    0.08
     Präsent
    0.08
     предъяв
    0.08
    Activations Density 0.011%

    No Known Activations