Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 103192
    Prev
    Next
    INDEX
    Explanations

    year

    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
     المؤ
    -0.08
     juvenil
    -0.08
     rango
    -0.07
     مؤ
    -0.07
     range
    -0.07
    улат
    -0.07
     хү
    -0.07
     jeunesse
    -0.07
     Ир
    -0.07
     repository
    -0.07
    POSITIVE LOGITS
    servername
    0.08
     grandma
    0.07
    zcan
    0.07
     pasti
    0.07
     elbows
    0.07
    fav
    0.07
    .sep
    0.07
     disagree
    0.07
     bargain
    0.07
    _DAMAGE
    0.07
    Activations Density 0.011%

    No Known Activations