© 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. 11-RESID-POST-AA
    6. 844
    Prev
    Next
    INDEX
    Explanations

    healthy/normal

    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
     Lleg
    -0.08
    .pad
    -0.08
     Deprecated
    -0.07
    pad
    -0.07
     deprecated
    -0.07
    ieli
    -0.07
     efectiva
    -0.07
    raw
    -0.07
    spam
    -0.07
     Maxim
    -0.07
    POSITIVE LOGITS
    正常
    0.15
     normal
    0.12
     healthy
    0.12
     정상
    0.11
     normale
    0.11
    normal
    0.10
    Normal
    0.10
     normalen
    0.10
     स्वस्थ
    0.10
    NORMAL
    0.10
    Activations Density 0.034%

    No Known Activations