© 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. 108473
    Prev
    Next
    INDEX
    Explanations

    Rock paper scissors

    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
     fundraising
    -0.08
    募
    -0.08
     Höhe
    -0.08
    ியே
    -0.08
    Neil
    -0.08
    Di
    -0.08
     accumulating
    -0.08
     JUN
    -0.08
    aktur
    -0.07
    Joining
    -0.07
    POSITIVE LOGITS
     matchup
    0.11
    拳
    0.10
     defeated
    0.10
     advant
    0.09
    三个
    0.09
     defending
    0.09
    rock
    0.09
     defeating
    0.09
     rock
    0.09
    .weapon
    0.09
    Activations Density 0.005%

    No Known Activations