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. 43732
    Prev
    Next
    INDEX
    Explanations

    carrots

    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
     GAS
    -0.08
     каж
    -0.08
     phases
    -0.08
     Wein
    -0.08
     tarp
    -0.07
    _MSG
    -0.07
     тро
    -0.07
     phạm
    -0.07
    owie
    -0.07
     Mittel
    -0.07
    POSITIVE LOGITS
    aments
    0.09
     punch
    0.08
     pues
    0.08
    绍
    0.08
     pencils
    0.08
     Semi
    0.08
    -pencil
    0.08
     segmented
    0.07
    -filter
    0.07
    宝宝
    0.07
    Activations Density 0.004%

    No Known Activations