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. 23-RESID-POST-AA
    6. 98027
    Prev
    Next
    INDEX
    Explanations

    مل

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    берите
    -0.07
    z
    -0.07
    fel
    -0.07
    zyme
    -0.07
    透
    -0.07
    zym
    -0.07
    듯
    -0.07
    价
    -0.07
     телефону
    -0.07
     trough
    -0.07
    POSITIVE LOGITS
    همة
    0.12
    هم
    0.10
    endan
    0.09
    nown
    0.09
    lican
    0.08
    Бар
    0.08
     Engeland
    0.08
    orde
    0.08
     Бар
    0.08
    reč
    0.07
    Activations Density 0.000%

    No Known Activations