© 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. 94385
    Prev
    Next
    INDEX
    Explanations

    Mathematical properties and functions

    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
    utral
    -0.08
     vegan
    -0.08
     abstra
    -0.08
     taane
    -0.07
     mantra
    -0.07
     barb
    -0.07
    Exceeded
    -0.07
    omac
    -0.07
    口
    -0.07
    Generic
    -0.07
    POSITIVE LOGITS
     Divorce
    0.08
     RIGHTS
    0.08
     雷
    0.08
     impar
    0.08
    eel
    0.07
     congressional
    0.07
    546
    0.07
     RIGHT
    0.07
     Giles
    0.07
    поч
    0.07
    Activations Density 0.002%

    No Known Activations