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. 65723
    Prev
    Next
    INDEX
    Explanations

    code-like text

    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
    Yet
    -0.08
     fól
    -0.08
     posse
    -0.08
    初心
    -0.08
    പ്പോ
    -0.08
    posed
    -0.08
     experiências
    -0.08
     aucune
    -0.07
    .xlsx
    -0.07
     kokem
    -0.07
    POSITIVE LOGITS
     Grade
    0.08
    Grade
    0.07
     anew
    0.07
     کرده
    0.07
     Taste
    0.07
     perfumes
    0.07
     Ull
    0.07
     expanded
    0.07
     oint
    0.07
    GRADE
    0.07
    Activations Density 0.003%

    No Known Activations