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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 75998
    Prev
    Next
    INDEX
    Explanations

    digital content/communication

    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
     Eller
    -0.08
     있기
    -0.08
     Toile
    -0.08
     Monument
    -0.08
    ിയും
    -0.08
     totiž
    -0.08
     pregunt
    -0.08
     else's
    -0.08
     bijvoorbeeld
    -0.08
     Sprite
    -0.08
    POSITIVE LOGITS
     TH
    0.07
    amp
    0.07
     secure
    0.07
     Dj
    0.07
    gen
    0.07
    thermal
    0.07
     AK
    0.07
    _T
    0.07
    itive
    0.06
    lem
    0.06
    Activations Density 0.228%

    No Known Activations