© 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. 75703
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
     uterus
    -0.08
    吗
    -0.08
    스를
    -0.08
     که
    -0.08
     Caldwell
    -0.07
    Stages
    -0.07
     hmm
    -0.07
     scor
    -0.07
     Frog
    -0.07
     shimmering
    -0.07
    POSITIVE LOGITS
     perspectives
    0.09
     POV
    0.08
    -made
    0.08
     Japon
    0.08
     pain
    0.08
     Perspectives
    0.07
     viewpoints
    0.07
     pleasure
    0.07
    working
    0.07
     paramount
    0.07
    Activations Density 0.385%

    No Known Activations