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. 30772
    Prev
    Next
    INDEX
    Explanations

    to

    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
     ensure
    -0.07
     questions
    -0.07
     काय
    -0.07
     assess
    -0.07
     göz
    -0.07
     pr
    -0.07
     تؤ
    -0.07
     Pro
    -0.07
     जो
    -0.07
     प्र
    -0.07
    POSITIVE LOGITS
     wholeheartedly
    0.09
     Higgins
    0.09
    hum
    0.08
     syndicated
    0.08
    惠
    0.08
     March
    0.08
    úl
    0.08
     Viv
    0.07
    ικη
    0.07
    March
    0.07
    Activations Density 0.031%

    No Known Activations