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. 131068
    Prev
    Next
    INDEX
    Explanations

    Maize

    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
     Certificates
    -0.08
     tiket
    -0.08
     മാന
    -0.08
     medan
    -0.08
     ӯ
    -0.08
     nais
    -0.08
     probation
    -0.08
     ஆல
    -0.08
     फीस
    -0.08
    agiste
    -0.08
    POSITIVE LOGITS
    Explain
    0.08
     explaining
    0.08
     erklären
    0.08
     morbidity
    0.08
    rp
    0.07
    mst
    0.07
    eko
    0.07
     supplemented
    0.07
    388
    0.07
    .compile
    0.07
    Activations Density 0.003%

    No Known Activations