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. 49220
    Prev
    Next
    INDEX
    Explanations

    logical reasoning

    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
    等等
    -0.08
     entsprechenden
    -0.08
    有所
    -0.08
     entsprech
    -0.08
     unser
    -0.08
     uyğun
    -0.08
     juist
    -0.08
     afterward
    -0.08
     bli
    -0.08
     vorz
    -0.07
    POSITIVE LOGITS
     Naked
    0.08
    _dt
    0.07
     Door
    0.07
    Door
    0.07
     있고
    0.07
     என்பது
    0.07
    _s
    0.07
     Piso
    0.07
    Paren
    0.07
     Wax
    0.07
    Activations Density 0.229%

    No Known Activations