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. 98848
    Prev
    Next
    INDEX
    Explanations

    heat

    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
     réd
    -0.08
    IMPORTANT
    -0.08
    ımız
    -0.07
    NOTE
    -0.07
    Makes
    -0.07
    B
    -0.07
    ***↵↵
    -0.07
    ais
    -0.07
    重大
    -0.07
    But
    -0.06
    POSITIVE LOGITS
     gee
    0.09
     तेज
    0.08
     bitters
    0.08
    adah
    0.08
    क्कर
    0.08
     ụtọ
    0.08
     gedurende
    0.08
    ssel
    0.08
    推广
    0.08
     vistazo
    0.08
    Activations Density 0.012%

    No Known Activations