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. 19246
    Prev
    Next
    INDEX
    Explanations

    variety

    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
     Entire
    -0.08
     Gaut
    -0.08
     Beng
    -0.08
     Billy
    -0.08
     Früh
    -0.07
     Karl
    -0.07
     ideales
    -0.07
     privées
    -0.07
     lý
    -0.07
     kokon
    -0.07
    POSITIVE LOGITS
     متنوعة
    0.12
     разнообраз
    0.12
     diversity
    0.12
     soorten
    0.11
     macam
    0.11
    種類
    0.11
     çeşit
    0.11
    玩法
    0.10
     Vielfalt
    0.10
     diversify
    0.10
    Activations Density 0.039%

    No Known Activations