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. 13047
    Prev
    Next
    INDEX
    Explanations

    turn

    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
    equ
    -0.09
    arity
    -0.08
     committed
    -0.08
     tér
    -0.07
    oes
    -0.07
     contradiction
    -0.07
     verse
    -0.07
    number
    -0.07
    Nation
    -0.07
     desenc
    -0.07
    POSITIVE LOGITS
     mica
    0.09
    vela
    0.08
    هم
    0.08
     Celsius
    0.08
    查看
    0.08
     santo
    0.08
     ceci
    0.08
     Wick
    0.07
     utmost
    0.07
     убед
    0.07
    Activations Density 0.010%

    No Known Activations