© 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. 11-RESID-POST-AA
    11. 68835
    Prev
    Next
    INDEX
    Explanations

    assess

    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
    ścia
    -0.08
     Æ
    -0.08
    вы
    -0.08
     verse
    -0.07
    atak
    -0.07
    دوز
    -0.07
     atr
    -0.07
     Stereo
    -0.07
     parted
    -0.07
    -за
    -0.07
    POSITIVE LOGITS
    一下
    0.09
     Bren
    0.08
     tenderness
    0.08
    ируем
    0.08
     Lewis
    0.07
    ически
    0.07
     paw
    0.07
    师
    0.07
    Lewis
    0.07
     crít
    0.07
    Activations Density 0.032%

    No Known Activations