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. 78550
    Prev
    Next
    INDEX
    Explanations

    "V" letter/shape and VISA

    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
     or
    -0.08
     rounded
    -0.08
    -0.08
     within
    -0.08
    24
    -0.08
     content
    -0.08
    .
    -0.07
     या
    -0.07
     ya
    -0.07
    ();
    -0.07
    POSITIVE LOGITS
     relação
    0.09
     wikipedia
    0.09
    ちなみに
    0.09
     welk
    0.09
    Congrats
    0.09
     Wifi
    0.09
     Walmart
    0.08
     hilarious
    0.08
     przec
    0.08
     nade
    0.08
    Activations Density 0.011%

    No Known Activations