© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44855
    Prev
    Next
    INDEX
    Explanations

    которая

    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
    上市
    -0.08
     backbone
    -0.08
    global
    -0.07
     footprint
    -0.07
    CCI
    -0.07
     Fitzgerald
    -0.07
     annex
    -0.07
     commission
    -0.07
    ，用
    -0.07
    .translate
    -0.07
    POSITIVE LOGITS
     tutors
    0.10
    ificance
    0.09
     डॉक्टर
    0.08
     গুরুত্ব
    0.08
     وكل
    0.08
     doctors
    0.08
     doctor's
    0.08
     barber
    0.08
     Milton
    0.08
     tadi
    0.08
    Activations Density 0.001%

    No Known Activations