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. 7-RESID-POST-AA
    6. 130988
    Prev
    Next
    INDEX
    Explanations

    willing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accent
    -0.07
     aficionados
    -0.07
    _HAL
    -0.07
     fossils
    -0.07
     perf
    -0.07
     neu
    -0.07
     ਕੁ
    -0.07
     edible
    -0.07
    tro
    -0.07
    Accent
    -0.07
    POSITIVE LOGITS
     lis
    0.09
    -minded
    0.08
     Tanner
    0.08
     Wholesale
    0.08
    HN
    0.08
     wax
    0.08
     AA
    0.08
     cro
    0.08
    wax
    0.07
     Reiki
    0.07
    Activations Density 0.010%

    No Known Activations