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. 45
    Prev
    Next
    INDEX
    Explanations

    Square root equations

    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
     fares
    -0.09
     confines
    -0.09
     stalls
    -0.08
     enää
    -0.08
     fare
    -0.08
    pens
    -0.08
     مغ
    -0.08
    heart
    -0.08
    wolves
    -0.08
     أع
    -0.08
    POSITIVE LOGITS
     positive
    0.10
     atan
    0.09
     positif
    0.09
     positieve
    0.09
     порядок
    0.08
     Positive
    0.08
     направление
    0.08
     inverse
    0.08
     অনুয
    0.08
    阳
    0.08
    Activations Density 0.007%

    No Known Activations