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. 77224
    Prev
    Next
    INDEX
    Explanations

    response

    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
     complexities
    -0.08
    ':↵
    -0.08
    ]:↵
    -0.07
    ":↵
    -0.07
     Belast
    -0.07
    estinal
    -0.07
    έα
    -0.07
    Ink
    -0.07
    ek
    -0.07
     importance
    -0.07
    POSITIVE LOGITS
     fraudulent
    0.09
    诈骗
    0.09
     offending
    0.09
     bait
    0.08
     Plaintiff
    0.08
     աշխատ
    0.08
    诈
    0.08
    陷
    0.08
     misinformation
    0.08
     bogus
    0.08
    Activations Density 0.002%

    No Known Activations