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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 13014
    Prev
    Next
    INDEX
    Explanations

    文本

    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
    Mang
    -0.08
     inso
    -0.07
    Sher
    -0.07
     изб
    -0.07
    rema
    -0.07
    ("***
    -0.07
    (search
    -0.07
    हा
    -0.07
     yük
    -0.07
    ented
    -0.07
    POSITIVE LOGITS
     TT
    0.08
     discounts
    0.08
    실
    0.07
     Accordingly
    0.07
     minuta
    0.07
     tactical
    0.07
     EPA
    0.07
     timedelta
    0.07
     electr
    0.07
     proximal
    0.07
    Activations Density 0.002%

    No Known Activations