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. 9027
    Prev
    Next
    INDEX
    Explanations

    automation

    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
     Lake
    -0.09
     lived
    -0.08
     Savannah
    -0.07
    ാരി
    -0.07
     disip
    -0.07
     സഹ
    -0.07
     Omar
    -0.07
     दर्ज
    -0.07
     Everton
    -0.07
    nor
    -0.07
    POSITIVE LOGITS
    -assisted
    0.09
     امور
    0.08
    /manual
    0.08
    성을
    0.08
    0.08
    изирован
    0.08
     tareas
    0.08
     aspects
    0.07
    (document
    0.07
     chores
    0.07
    Activations Density 0.012%

    No Known Activations