Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 56155
    Prev
    Next
    INDEX
    Explanations

    top

    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
    ei
    -0.08
    ockey
    -0.08
     tsunami
    -0.08
    tern
    -0.08
    acus
    -0.07
    共
    -0.07
     sup
    -0.07
     dur
    -0.07
    aliment
    -0.07
    -0.07
    POSITIVE LOGITS
     Blu
    0.08
    :white
    0.08
     cielo
    0.08
    	wire
    0.08
     blu
    0.07
     prender
    0.07
     сл
    0.07
     منابع
    0.07
     antennas
    0.07
     wire
    0.07
    Activations Density 0.006%

    No Known Activations