© 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. 108135
    Prev
    Next
    INDEX
    Explanations

    evolutionary psychology

    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
     lifts
    -0.09
     lifting
    -0.08
     lift
    -0.07
    International
    -0.07
    lift
    -0.07
     lifted
    -0.07
     kilometr
    -0.07
     আন্তর্জাতিক
    -0.07
     (
    -0.07
    lifting
    -0.07
    POSITIVE LOGITS
     perigo
    0.09
    omone
    0.09
     haw
    0.09
     kai
    0.09
     hunter
    0.09
    ourage
    0.08
     criança
    0.08
     cognition
    0.08
     Shepard
    0.08
    ラー
    0.08
    Activations Density 0.029%

    No Known Activations