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. 52996
    Prev
    Next
    INDEX
    Explanations

    rather

    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
    _sys
    -0.08
     Cs
    -0.07
    tionen
    -0.07
    ach
    -0.07
     Lach
    -0.07
    proj
    -0.07
    к
    -0.07
    Clin
    -0.07
    cep
    -0.07
    46
    -0.07
    POSITIVE LOGITS
     Brook
    0.08
     Freder
    0.08
    િણ
    0.08
     बु
    0.07
    Brook
    0.07
    ANSI
    0.07
    门户
    0.07
     buck
    0.07
     perfection
    0.07
     dens
    0.07
    Activations Density 0.009%

    No Known Activations