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. 98258
    Prev
    Next
    INDEX
    Explanations

    dans

    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
    IZED
    -0.09
    IZATION
    -0.09
    ספר
    -0.09
     кафед
    -0.08
     때문에
    -0.08
     overlijden
    -0.08
    IZE
    -0.08
    _again
    -0.08
    ρθ
    -0.08
     સામે
    -0.08
    POSITIVE LOGITS
     lequel
    0.16
     рамках
    0.14
     laquelle
    0.14
     lesquels
    0.14
     âmbito
    0.14
     vitro
    0.13
     lesquelles
    0.12
     votre
    0.12
     maniera
    0.12
     cadrul
    0.12
    Activations Density 0.006%

    No Known Activations