© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6432
    Prev
    Next
    INDEX
    Explanations

    Cyrillic "р" or "r"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encom
    -0.09
    latable
    -0.09
    umelela
    -0.08
     vot
    -0.08
    ля
    -0.08
     Alison
    -0.08
     Likes
    -0.08
    朋友圈
    -0.08
    SSFCell
    -0.08
    aryti
    -0.08
    POSITIVE LOGITS
    ంధ్ర
    0.09
    ubble
    0.09
    ips
    0.08
    eseat
    0.08
    ender
    0.08
    жав
    0.08
    ipmap
    0.07
    ipping
    0.07
    ods
    0.07
    erase
    0.07
    Activations Density 0.017%

    No Known Activations