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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77870
    Prev
    Next
    INDEX
    Explanations

    Weighing puzzles

    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
    erialization
    -0.08
    vertical
    -0.08
     feststellen
    -0.08
    ெர
    -0.08
    pathname
    -0.08
     мом
    -0.08
    تمان
    -0.08
     江
    -0.08
     vertical
    -0.07
     verticale
    -0.07
    POSITIVE LOGITS
     милли
    0.08
     embryos
    0.08
    Weighted
    0.08
    Balanced
    0.08
    balanced
    0.08
     भार
    0.08
    об
    0.08
     weighting
    0.07
     MIL
    0.07
     //[
    0.07
    Activations Density 0.003%

    No Known Activations