© 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. 23-RESID-POST-AA
    6. 49041
    Prev
    Next
    INDEX
    Explanations

    hippie counterculture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lietuvos
    -0.08
     ioh
    -0.08
    200
    -0.08
     specimen
    -0.08
     koy
    -0.07
    _DC
    -0.07
     við
    -0.07
    [random
    -0.07
     bino
    -0.07
     specimens
    -0.07
    POSITIVE LOGITS
     psychedelic
    0.17
     Vietnam
    0.16
     counter
    0.15
     psyched
    0.13
     hipp
    0.13
    counter
    0.13
     flower
    0.13
    .counter
    0.12
     Counter
    0.12
     Woodstock
    0.12
    Activations Density 0.031%

    No Known Activations