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. 88057
    Prev
    Next
    INDEX
    Explanations

    Space weather and communication

    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
     remorse
    -0.09
     ips
    -0.08
     sacrificed
    -0.08
     put
    -0.08
    /header
    -0.08
     apologies
    -0.08
     insults
    -0.08
    ROI
    -0.08
     unst
    -0.08
    核心
    -0.07
    POSITIVE LOGITS
     предупреж
    0.10
     инженер
    0.09
     engineers
    0.09
     Engineering
    0.09
    Engineering
    0.09
     автомобил
    0.09
     полез
    0.08
     магнит
    0.08
     медицина
    0.08
     Engineers
    0.08
    Activations Density 0.041%

    No Known Activations