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. 45110
    Prev
    Next
    INDEX
    Explanations

    Speech or statements

    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
     elusive
    -0.09
    Column
    -0.08
     clearance
    -0.08
     вами
    -0.07
    -have
    -0.07
    LES
    -0.07
    ovane
    -0.07
    228
    -0.07
     precar
    -0.07
     elenco
    -0.07
    POSITIVE LOGITS
     بذلك
    0.08
     chỉnh
    0.08
     Essa
    0.07
     notably
    0.07
    认为
    0.07
     giáo
    0.07
    ritter
    0.07
    骑
    0.07
     بأنها
    0.07
    :update
    0.07
    Activations Density 0.090%

    No Known Activations