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. 27160
    Prev
    Next
    INDEX
    Explanations

    水 (water)

    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
     pearl
    -0.08
     cran
    -0.07
    袖
    -0.07
     käyt
    -0.07
    ซี
    -0.07
     connaître
    -0.07
     chew
    -0.07
     Wrest
    -0.07
     bra
    -0.07
     crushers
    -0.07
    POSITIVE LOGITS
     scenery
    0.09
     scenic
    0.09
     paysages
    0.08
    .pyplot
    0.08
    uthor
    0.08
     watercolor
    0.08
     encountered
    0.08
    문
    0.08
    _png
    0.08
     фотографии
    0.07
    Activations Density 0.011%

    No Known Activations