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. 60804
    Prev
    Next
    INDEX
    Explanations

    job postings

    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
    汁
    -0.09
     كلها
    -0.08
     rehetra
    -0.07
     camada
    -0.07
     Edwin
    -0.07
     billions
    -0.07
     airborne
    -0.07
     watery
    -0.07
     كله
    -0.07
     stronie
    -0.07
    POSITIVE LOGITS
    职责
    0.09
     Responsibilities
    0.08
    Responsibilities
    0.08
     ಎಂಬ
    0.08
    Inbound
    0.08
    stead
    0.08
    byg
    0.08
    akanaka
    0.08
     duties
    0.08
    бас
    0.08
    Activations Density 0.045%

    No Known Activations