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. 60806
    Prev
    Next
    INDEX
    Explanations

    hiding

    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
    性生活
    -0.07
    -p
    -0.07
    uum
    -0.07
    eins
    -0.07
     glue
    -0.07
     sleeve
    -0.07
     rotary
    -0.07
     Glue
    -0.07
    Sq
    -0.07
     هي
    -0.07
    POSITIVE LOGITS
     atë
    0.09
    遮
    0.09
     hides
    0.09
     shielding
    0.08
     blinded
    0.08
    ाछ
    0.08
     Certains
    0.08
    ^
    0.08
     compatri
    0.08
    ႀ
    0.08
    Activations Density 0.001%

    No Known Activations