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. 111637
    Prev
    Next
    INDEX
    Explanations

    Time-related statistics

    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
    geschlossen
    -0.08
     contrari
    -0.08
     modifier
    -0.07
     modifiers
    -0.07
    UMIN
    -0.07
     Get
    -0.07
    uller
    -0.07
     содерж
    -0.07
     Option
    -0.07
     коррект
    -0.07
    POSITIVE LOGITS
    一分钟
    0.11
     births
    0.10
    不停
    0.10
     લાખ
    0.10
     જન્મ
    0.09
    .spawn
    0.09
     全球
    0.09
    每天
    0.09
     लाख
    0.09
     wachsen
    0.09
    Activations Density 0.027%

    No Known Activations