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. 30411
    Prev
    Next
    INDEX
    Explanations

    black holes

    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
    -ти
    -0.08
     lb
    -0.08
     treaties
    -0.08
     tint
    -0.08
     tự
    -0.08
     lunar
    -0.08
     birthdays
    -0.07
     Lavender
    -0.07
    	mouse
    -0.07
    ,start
    -0.07
    POSITIVE LOGITS
     powering
    0.09
     jets
    0.08
     السلطة
    0.08
     вращ
    0.08
     തട
    0.08
     വരുന്ന
    0.07
    ourses
    0.07
     phenomena
    0.07
    挥
    0.07
     функциони
    0.07
    Activations Density 0.002%

    No Known Activations