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. 73
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    uture
    -0.10
    ort
    -0.08
    ibid
    -0.08
    obot
    -0.08
    itas
    -0.08
    utr
    -0.08
    idagi
    -0.08
    bildungs
    -0.08
    inet
    -0.08
    .bas
    -0.08
    POSITIVE LOGITS
     сейчас
    0.09
     thôi
    0.09
     هنا
    0.09
     зл
    0.08
     распространя
    0.08
     немного
    0.08
     here
    0.08
     получает
    0.08
     зараз
    0.08
     разных
    0.08
    Activations Density 0.001%

    No Known Activations