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. 183
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    Katika
    -0.09
    zame
    -0.09
     dalka
    -0.09
    šanu
    -0.08
    ៀត
    -0.08
     labada
    -0.08
    “To
    -0.08
     сваіх
    -0.08
    ternate
    -0.08
    იის
    -0.08
    POSITIVE LOGITS
    1
    0.14
    ১
    0.13
    १
    0.11
    ①
    0.11
     Overview
    0.10
     اول
    0.10
     الأول
    0.10
    01
    0.10
     pertama
    0.10
    ١
    0.10
    Activations Density 0.014%

    No Known Activations