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. 30310
    Prev
    Next
    INDEX
    Explanations

    Male pronoun

    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
     chí
    -0.08
     khí
    -0.08
     Aluminum
    -0.08
    障
    -0.08
     PIN
    -0.08
     committed
    -0.08
     бю
    -0.08
     Quarterly
    -0.08
     Pues
    -0.08
     Rear
    -0.07
    POSITIVE LOGITS
     miracles
    0.11
     preaching
    0.09
     mirac
    0.09
     miracle
    0.09
     preached
    0.08
     barefoot
    0.08
     milag
    0.08
    Collection
    0.08
     atraer
    0.08
     teachings
    0.08
    Activations Density 0.018%

    No Known Activations