© 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. 94747
    Prev
    Next
    INDEX
    Explanations

    assists

    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
     cire
    -0.09
     bale
    -0.08
     mou
    -0.08
    oud
    -0.08
     fys
    -0.08
     alim
    -0.08
     körper
    -0.08
     Mink
    -0.08
    lector
    -0.08
     Physical
    -0.07
    POSITIVE LOGITS
     흐
    0.08
     сет
    0.08
     Innoc
    0.08
    Sac
    0.08
     duties
    0.08
     обязан
    0.08
     несмотря
    0.08
    Ack
    0.07
     зг
    0.07
     quarterback
    0.07
    Activations Density 0.013%

    No Known Activations