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. 3-RESID-POST-AA
    6. 12367
    Prev
    Next
    INDEX
    Explanations

    太

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cam
    -0.08
     tia
    -0.08
     hod
    -0.07
     Geoffrey
    -0.07
     baker
    -0.07
     expert
    -0.07
     Nin
    -0.07
     caisse
    -0.07
     jur
    -0.07
     mas
    -0.07
    POSITIVE LOGITS
     afin
    0.09
     Chal
    0.09
     Vid
    0.08
     fino
    0.07
    棒
    0.07
    দিন
    0.07
     phenomen
    0.07
    bull
    0.07
     Alas
    0.07
    য়া
    0.07
    Activations Density 0.004%

    No Known Activations