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. 55962
    Prev
    Next
    INDEX
    Explanations

    editorial

    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
     hybrid
    -0.08
     modalities
    -0.08
    lau
    -0.08
     proto
    -0.08
     accurately
    -0.07
    proto
    -0.07
     identify
    -0.07
     prototypes
    -0.07
     perfectly
    -0.07
     modality
    -0.07
    POSITIVE LOGITS
     Tint
    0.09
     jornalistas
    0.09
     Grammarly
    0.09
     редак
    0.08
     viên
    0.08
     чәк
    0.08
     proofreading
    0.08
     Editorial
    0.08
     글
    0.08
    Signin
    0.08
    Activations Density 0.012%

    No Known Activations