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. 78176
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ()]
    -0.09
     lượng
    -0.08
     excitement
    -0.08
     festive
    -0.08
    ொ
    -0.08
    libraries
    -0.08
     shipment
    -0.08
    ياء
    -0.08
     irresponsible
    -0.08
    ृत
    -0.08
    POSITIVE LOGITS
    axis
    0.08
    660
    0.08
     axis
    0.08
     Good
    0.07
     warp
    0.07
    entz
    0.07
     good
    0.07
     ots
    0.07
    aked
    0.07
     (
    0.07
    Activations Density 0.024%

    No Known Activations