Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 106254
    Prev
    Next
    INDEX
    Explanations

    agine

    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
    kenn
    -0.08
    orma
    -0.07
     myth
    -0.07
    inty
    -0.07
     Rogers
    -0.07
    anku
    -0.07
    ిల
    -0.07
    amam
    -0.07
    特点
    -0.07
     exhaust
    -0.07
    POSITIVE LOGITS
    (())↵
    0.09
     grads
    0.08
    Scrolling
    0.08
     순간
    0.07
     Ав
    0.07
     바로
    0.07
    ∀
    0.07
    Dato
    0.07
     olar
    0.07
    UInteger
    0.07
    Activations Density 0.008%

    No Known Activations