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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 120373
    Prev
    Next
    INDEX
    Explanations

    per second

    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
     komple
    -0.08
     Sul
    -0.08
     Vega
    -0.07
     sulfur
    -0.07
    -0.07
    _q
    -0.07
     بحيث
    -0.07
     Throw
    -0.07
     детали
    -0.07
    örungen
    -0.07
    POSITIVE LOGITS
     gedurende
    0.13
     accru
    0.13
     contín
    0.12
     continuously
    0.12
     tick
    0.11
     accrued
    0.11
    during
    0.11
     accrue
    0.11
    tick
    0.11
     incurred
    0.11
    Activations Density 0.022%

    No Known Activations