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. 90761
    Prev
    Next
    INDEX
    Explanations

    new, newly

    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
    ץ
    -0.09
     downs
    -0.08
    phal
    -0.08
     congenital
    -0.07
     Jakob
    -0.07
    clf
    -0.07
     Sims
    -0.07
     ссыл
    -0.07
     автомат
    -0.07
     cref
    -0.07
    POSITIVE LOGITS
     fresh
    0.10
     recently
    0.10
     recién
    0.09
     freshly
    0.09
     తాజాగా
    0.09
     ترین
    0.09
     récente
    0.09
     freshness
    0.09
     недавно
    0.09
     recientemente
    0.09
    Activations Density 0.067%

    No Known Activations