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. 15-RESID-POST-AA
    6. 89
    Prev
    Next
    INDEX
    Explanations

    Describing points beyond another

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    هر
    -0.08
    -0.08
    夜夜
    -0.08
    aps
    -0.08
    abort
    -0.08
    ✅
    -0.07
    opio
    -0.07
     সাজ
    -0.07
    .total
    -0.07
    .il
    -0.07
    POSITIVE LOGITS
     towards
    0.10
     مشتری
    0.09
     तरफ
    0.09
     خدا
    0.08
    _FROM
    0.08
    ERVER
    0.08
    ários
    0.08
    -facing
    0.08
     toward
    0.08
     ग्राहक
    0.08
    Activations Density 0.007%

    No Known Activations