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. 75958
    Prev
    Next
    INDEX
    Explanations

    assets

    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
     braided
    -0.09
     gezonde
    -0.09
     sewing
    -0.08
    caf
    -0.08
     saludable
    -0.08
     braid
    -0.08
    _cod
    -0.08
    COLOR
    -0.08
     voel
    -0.08
     clen
    -0.08
    POSITIVE LOGITS
     efficiency
    0.08
     eficiência
    0.08
     दक्ष
    0.08
     भ
    0.08
    টো
    0.07
     Efficiency
    0.07
    ური
    0.07
    Efficiency
    0.07
     modest
    0.07
     effectiveness
    0.07
    Activations Density 0.002%

    No Known Activations