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. 15-RESID-POST-AA
    6. 192
    Prev
    Next
    INDEX
    Explanations

    Different

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specifically
    -0.08
     prona
    -0.08
    なら
    -0.07
     específicamente
    -0.07
     particularly
    -0.07
    halten
    -0.07
     обратить
    -0.07
    -inspired
    -0.07
     indique
    -0.07
    ర్ట
    -0.07
    POSITIVE LOGITS
    Different
    0.09
    Either
    0.09
     diferente
    0.09
    Mostly
    0.09
    Inheritance
    0.09
    Inherited
    0.09
     unterschiedliche
    0.09
    different
    0.09
    ,因此
    0.09
     unterschiedlich
    0.09
    Activations Density 0.055%

    No Known Activations