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. 120312
    Prev
    Next
    INDEX
    Explanations

    酸

    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
     Latin
    -0.07
     Ges
    -0.07
    arpa
    -0.07
     Physician
    -0.07
     fiscal
    -0.07
    mig
    -0.07
     לעצ
    -0.07
    elopen
    -0.07
    >((
    -0.07
    fras
    -0.06
    POSITIVE LOGITS
     bou
    0.08
    óm
    0.08
     fumes
    0.07
     lòt
    0.07
     तत्व
    0.07
     mingle
    0.07
     formatted
    0.07
    HTMLElement
    0.07
     izinto
    0.07
     spé
    0.07
    Activations Density 0.004%

    No Known Activations