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. 23-RESID-POST-AA
    6. 130754
    Prev
    Next
    INDEX
    Explanations

    mineral

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ингов
    -0.09
     Garantie
    -0.08
    -0.08
     Gig
    -0.08
    INGTON
    -0.08
    sterdam
    -0.08
     سام
    -0.08
     رپور
    -0.08
     Gamma
    -0.08
     ক্ষম
    -0.08
    POSITIVE LOGITS
    ogical
    0.14
    og
    0.12
    ogy
    0.11
     minera
    0.10
     oil
    0.09
    oc
    0.09
     supplementation
    0.09
    ógico
    0.09
    Oil
    0.09
    isir
    0.09
    Activations Density 0.003%

    No Known Activations