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. 119382
    Prev
    Next
    INDEX
    Explanations

    demonstrate

    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
    /new
    -0.09
    -fashioned
    -0.08
     निक
    -0.08
     pocket
    -0.08
    peed
    -0.08
     residencial
    -0.08
    қа
    -0.07
    quart
    -0.07
     Cre
    -0.07
     BK
    -0.07
    POSITIVE LOGITS
     Expert
    0.08
    ಿಂದ
    0.07
    /demo
    0.07
     tofu
    0.07
     пример
    0.07
     принес
    0.07
    ات
    0.07
     Lia
    0.07
     cable
    0.07
     cam
    0.07
    Activations Density 0.013%

    No Known Activations