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. 23-RESID-POST-AA
    6. 130930
    Prev
    Next
    INDEX
    Explanations

    Great Wall length, square roots

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poter
    -0.08
     FIR
    -0.08
     Mauricio
    -0.08
    тар
    -0.08
     Booster
    -0.07
     fueran
    -0.07
     вен
    -0.07
     TValue
    -0.07
     connaître
    -0.07
     Cau
    -0.07
    POSITIVE LOGITS
    ít
    0.08
    ix
    0.08
    ức
    0.08
     વર્�
    0.07
    ionic
    0.07
    mods
    0.07
    inish
    0.07
     ವರ್�
    0.07
    ÍT
    0.07
     చర్య
    0.07
    Activations Density 0.000%

    No Known Activations