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. 7-RESID-POST-AA
    6. 1975
    Prev
    Next
    INDEX
    Explanations

    Chernobyl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tcp
    -0.08
    (port
    -0.08
    —which
    -0.08
    ৃতি
    -0.08
    ılar
    -0.07
    Dt
    -0.07
    Accounts
    -0.07
    port
    -0.07
     dementia
    -0.07
    -0.07
    POSITIVE LOGITS
     గ్ర
    0.09
     Lei
    0.09
     Leone
    0.09
     siege
    0.08
     తీవ్ర
    0.08
     Саб
    0.08
     Seele
    0.08
     lei
    0.08
     Zwischen
    0.08
    arii
    0.08
    Activations Density 0.001%

    No Known Activations