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. 12295
    Prev
    Next
    INDEX
    Explanations

    Mathematical notation

    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
    知识
    -0.09
     drive
    -0.08
    'eng
    -0.08
    详细
    -0.08
    'époque
    -0.07
    ə
    -0.07
    drive
    -0.07
     Kenntnisse
    -0.07
    时
    -0.07
    'aide
    -0.07
    POSITIVE LOGITS
    ineq
    0.09
     inequality
    0.09
    oser
    0.09
    Limiter
    0.08
     VK
    0.08
    صة
    0.08
     yayi
    0.08
    vre
    0.08
     Gon
    0.08
     inequalities
    0.07
    Activations Density 0.035%

    No Known Activations