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. 58684
    Prev
    Next
    INDEX
    Explanations

    ut

    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
    卷
    -0.08
    geving
    -0.08
    ләрни
    -0.08
     curry
    -0.08
    哈
    -0.08
     EXISTS
    -0.07
    赋
    -0.07
     autor
    -0.07
     لات
    -0.07
     Roland
    -0.07
    POSITIVE LOGITS
     пациента
    0.09
    Savings
    0.08
     Savings
    0.08
     gleich
    0.08
     patient's
    0.08
     komun
    0.08
    fæ
    0.08
    .Patient
    0.08
    mittel
    0.08
    konto
    0.08
    Activations Density 0.005%

    No Known Activations