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. 112018
    Prev
    Next
    INDEX
    Explanations

    system

    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
     والاج
    -0.09
    jus
    -0.08
     prüfen
    -0.08
    _NONNULL
    -0.08
    mern
    -0.08
     वा
    -0.08
     과정
    -0.08
     خلال
    -0.08
     어렵
    -0.08
     תוך
    -0.07
    POSITIVE LOGITS
    -chave
    0.09
     kerja
    0.09
     này
    0.08
     SHE
    0.08
     COS
    0.08
     ranging
    0.08
     CPI
    0.08
    های
    0.08
    การ
    0.07
     quản
    0.07
    Activations Density 0.154%

    No Known Activations