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. 120473
    Prev
    Next
    INDEX
    Explanations

    dreams and brain stimulation

    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
     excuse
    -0.09
    antik
    -0.08
     ant
    -0.08
     unlimited
    -0.08
    _mutex
    -0.08
     davor
    -0.08
     miễn
    -0.08
    irmek
    -0.08
     Antar
    -0.08
     antip
    -0.08
    POSITIVE LOGITS
    Path
    0.08
     terrestrial
    0.08
    .CLASS
    0.08
     значит
    0.08
     Zhu
    0.08
    PATH
    0.07
    Ut
    0.07
     تساعد
    0.07
    цен
    0.07
     徐
    0.07
    Activations Density 0.001%

    No Known Activations