Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 120238
    Prev
    Next
    INDEX
    Explanations

    internal heat

    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
     Peut
    -0.08
     embellished
    -0.08
    Frag
    -0.07
    ുഴ
    -0.07
    Nullable
    -0.07
     tecnica
    -0.07
    .Reference
    -0.07
     خطوة
    -0.07
     اي
    -0.07
    Pointers
    -0.07
    POSITIVE LOGITS
     sources
    0.12
     источ
    0.11
     स्रोत
    0.11
    ources
    0.11
     Sources
    0.11
    來源
    0.11
     fuente
    0.10
    来源
    0.10
     originating
    0.10
     ચાલુ
    0.10
    Activations Density 0.013%

    No Known Activations