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. 58595
    Prev
    Next
    INDEX
    Explanations

    dandelion

    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
    再次
    -0.08
    ore
    -0.07
    Mage
    -0.07
     repo
    -0.07
    /sign
    -0.07
     them
    -0.07
     nochmal
    -0.07
     Repo
    -0.07
    -0.07
    /met
    -0.07
    POSITIVE LOGITS
     tins
    0.09
     pineapple
    0.08
     Balm
    0.08
     Sno
    0.08
     creamy
    0.08
     松
    0.08
     graphite
    0.08
     Malay
    0.08
     вил
    0.08
     בעיקר
    0.08
    Activations Density 0.000%

    No Known Activations