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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47897
    Prev
    Next
    INDEX
    Explanations

    physics and math

    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
    ಗು
    -0.08
     Hare
    -0.08
    ]<
    -0.08
     USPS
    -0.08
     ವಿಭಾಗ
    -0.07
     пасп
    -0.07
     Jesu
    -0.07
     MAC
    -0.07
     чему
    -0.07
     вяр
    -0.07
    POSITIVE LOGITS
     distraction
    0.09
     distracting
    0.08
     distractions
    0.08
     irrit
    0.08
     khó
    0.08
     payable
    0.08
     distra
    0.08
    -param
    0.08
    encé
    0.07
    입
    0.07
    Activations Density 0.010%

    No Known Activations