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. 30025
    Prev
    Next
    INDEX
    Explanations

    survivors and being left

    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
     interchangeable
    -0.10
    اتها
    -0.10
     گل
    -0.09
     API
    -0.09
     библи
    -0.08
     oriṣ
    -0.08
     aṣa
    -0.08
     создания
    -0.08
     taps
    -0.08
     dpi
    -0.08
    POSITIVE LOGITS
     surviving
    0.09
     survivor
    0.09
    remaining
    0.09
     Remaining
    0.08
    剩
    0.08
    certe
    0.08
    mble
    0.08
     남
    0.08
    남
    0.07
    sur
    0.07
    Activations Density 0.014%

    No Known Activations