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

    Neuronpedia

    APICircuit 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. 88307
    Prev
    Next
    INDEX
    Explanations

    proceed

    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
     WV
    -0.08
    bildung
    -0.07
     davantage
    -0.07
     UFO
    -0.07
    elig
    -0.07
     MG
    -0.07
    IRONMENT
    -0.07
    Readable
    -0.07
     настро
    -0.07
    ecos
    -0.07
    POSITIVE LOGITS
    wards
    0.08
     desal
    0.08
     הלא
    0.08
     adelante
    0.08
    'exp
    0.08
     systematically
    0.07
    انه
    0.07
     unh
    0.07
    ’exp
    0.07
     Pare
    0.07
    Activations Density 0.006%

    No Known Activations