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. 44937
    Prev
    Next
    INDEX
    Explanations

    subtraction

    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
     ka
    -0.08
    oplevel
    -0.08
    iu
    -0.07
     além
    -0.07
     mk
    -0.07
     incoming
    -0.07
     forwarded
    -0.07
     decode
    -0.07
     vooral
    -0.07
     capacity
    -0.07
    POSITIVE LOGITS
     undesirable
    0.09
     creatively
    0.08
     صغيرة
    0.08
     Einer
    0.08
     edildi
    0.07
     తగ్గ
    0.07
    Covid
    0.07
    27
    0.07
     Disaster
    0.07
     Licensing
    0.07
    Activations Density 0.027%

    No Known Activations