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. 131022
    Prev
    Next
    INDEX
    Explanations

    Cryptocurrency

    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
     организа
    -0.08
    urm
    -0.08
    Spe
    -0.07
    spe
    -0.07
    htdocs
    -0.07
    ostal
    -0.07
     spe
    -0.07
     sludge
    -0.07
    -0.07
     Wahrscheinlichkeit
    -0.07
    POSITIVE LOGITS
     Rés
    0.08
    .Types
    0.08
     Dua
    0.07
    .Log
    0.07
    Résumé
    0.07
     obliv
    0.07
     zwa
    0.07
     bob
    0.07
     Hoover
    0.07
    اع
    0.07
    Activations Density 0.000%

    No Known Activations