Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12918
    Prev
    Next
    INDEX
    Explanations

    from

    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
     ರಂದು
    -0.09
    回复
    -0.08
     palaut
    -0.08
    ,但是
    -0.08
    ului
    -0.08
    �
    -0.08
    ueel
    -0.08
     下一
    -0.08
    。但是
    -0.08
    。另外
    -0.08
    POSITIVE LOGITS
     bench
    0.09
     Silver
    0.08
    Silver
    0.08
     mundane
    0.08
     drafting
    0.08
     conception
    0.07
    บ
    0.07
     Vin
    0.07
    0.07
     fog
    0.07
    Activations Density 0.018%

    No Known Activations