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. 75907
    Prev
    Next
    INDEX
    Explanations

    Knowledge

    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
     afirm
    -0.08
    California
    -0.08
     forc
    -0.08
     medically
    -0.08
    nton
    -0.08
     scl
    -0.07
     treaty
    -0.07
     afirmar
    -0.07
    adecimal
    -0.07
     projectile
    -0.07
    POSITIVE LOGITS
     tutorials
    0.14
    教程
    0.13
     FAQs
    0.13
     FAQ
    0.13
     Tutorials
    0.13
    FAQs
    0.13
    FAQ
    0.12
    Frequently
    0.10
     документа
    0.10
     Frequently
    0.10
    Activations Density 0.024%

    No Known Activations