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. 76745
    Prev
    Next
    INDEX
    Explanations

    emergency room

    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
    共
    -0.08
    乙
    -0.08
    σίας
    -0.08
     cipher
    -0.08
     ECB
    -0.07
    木
    -0.07
     τρί
    -0.07
    推广
    -0.07
     envelop
    -0.07
     pól
    -0.07
    POSITIVE LOGITS
    arrival
    0.09
     अस्पताल
    0.09
    taken
    0.09
    airport
    0.08
     reakc
    0.08
     entrance
    0.08
     violence
    0.08
    Crash
    0.08
     arrivals
    0.08
    shock
    0.08
    Activations Density 0.008%

    No Known Activations