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. 7-RESID-POST-AA
    6. 1728
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cer
    -0.08
     терапии
    -0.07
    ">'.$
    -0.07
    וגמא
    -0.07
     Cer
    -0.07
    กำ
    -0.07
     transmis
    -0.07
     bearing
    -0.07
    वी
    -0.07
     Montessori
    -0.07
    POSITIVE LOGITS
     wander
    0.08
     burst
    0.08
     wandering
    0.07
    Angel
    0.07
    нути
    0.07
     способность
    0.07
     Burst
    0.07
    eness
    0.07
     twitch
    0.07
     ಕಡ
    0.07
    Activations Density 0.146%

    No Known Activations