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. 15-RESID-POST-AA
    6. 18931
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enthe
    -0.09
     poderia
    -0.09
     everytime
    -0.08
     acrylic
    -0.08
     podria
    -0.08
    ู่
    -0.08
     ব্ল
    -0.08
    朋克
    -0.08
     präsent
    -0.08
    ,每
    -0.08
    POSITIVE LOGITS
    ":↵↵
    0.08
     विवरण
    0.08
    ":
    0.07
    _company
    0.07
     requirements
    0.07
     لازم
    0.07
    ."↵↵
    0.07
    722
    0.07
     شرح
    0.07
     आवश्यक
    0.07
    Activations Density 0.001%

    No Known Activations