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. 77028
    Prev
    Next
    INDEX
    Explanations

    低

    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
     supplementation
    -0.08
     Hef
    -0.08
    star
    -0.08
    you
    -0.08
    Das
    -0.08
     FED
    -0.08
    amientos
    -0.08
    Wilson
    -0.08
    dic
    -0.08
    YOU
    -0.07
    POSITIVE LOGITS
     fuss
    0.09
     downtime
    0.09
    oupe
    0.08
    ಗಿನ
    0.08
    امت
    0.08
     drv
    0.08
     Tweet
    0.08
     chipset
    0.07
     drift
    0.07
     bruit
    0.07
    Activations Density 0.005%

    No Known Activations