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. 11-RESID-POST-AA
    6. 43980
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
    -ele
    -0.07
    .Profile
    -0.07
     Electronic
    -0.07
     Jonathan
    -0.07
    ="#
    -0.07
     auditory
    -0.07
    �
    -0.07
    Group
    -0.07
     GROUP
    -0.07
     refr
    -0.07
    POSITIVE LOGITS
    부
    0.09
     schönsten
    0.09
    ïn
    0.08
     verkauft
    0.08
     spécialiste
    0.08
     ikon
    0.08
     Bür
    0.08
    ieltä
    0.08
     umwe
    0.08
     بيع
    0.08
    Activations Density 0.003%

    No Known Activations