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. 106130
    Prev
    Next
    INDEX
    Explanations

    quotation marks and commas

    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
     stabile
    -0.07
     siinä
    -0.07
     txoj
    -0.07
     oga
    -0.07
     samalla
    -0.07
     taxe
    -0.07
    的彩票
    -0.07
     algae
    -0.07
     seco
    -0.07
     junto
    -0.07
    POSITIVE LOGITS
    grad
    0.08
     появ
    0.08
    omy
    0.08
     Huffington
    0.08
     utilisés
    0.08
     подоб
    0.07
    .grad
    0.07
    etc
    0.07
    phr
    0.07
    (anim
    0.07
    Activations Density 0.026%

    No Known Activations