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. 97078
    Prev
    Next
    INDEX
    Explanations

    Ukrainian language

    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
     비롯
    -0.09
     миру
    -0.09
     své
    -0.09
    ные
    -0.09
     مناط
    -0.09
     рост
    -0.08
     мост
    -0.08
    য়ের
    -0.08
     společnosti
    -0.08
     доход
    -0.08
    POSITIVE LOGITS
     напад
    0.13
     спос
    0.13
     серв
    0.11
    лений
    0.11
     прост
    0.11
     náz
    0.11
    аний
    0.11
    сний
    0.10
     člán
    0.10
    lepší
    0.10
    Activations Density 0.006%

    No Known Activations