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. 97
    Prev
    Next
    INDEX
    Explanations

    有

    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
    Steve
    -0.10
    กิจ
    -0.09
    aurants
    -0.09
     ευρώ
    -0.08
    irio
    -0.08
    urations
    -0.08
    ilio
    -0.08
     அவர
    -0.08
     Ее
    -0.08
     مختلفة
    -0.08
    POSITIVE LOGITS
    些
    0.14
     besoin
    0.11
    นาคม
    0.11
    趣
    0.11
    时候
    0.11
    助
    0.10
    必要
    0.10
     been
    0.10
     necessidade
    0.09
    可能
    0.09
    Activations Density 0.008%

    No Known Activations