© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51987
    Prev
    Next
    INDEX
    Explanations

    say arousal

    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
    bekiston
    -0.08
     пришлось
    -0.08
    bagbogbo
    -0.08
     Blackjack
    -0.07
     treated
    -0.07
     ricord
    -0.07
    ību
    -0.07
    bone
    -0.07
     będą
    -0.07
     Lance
    -0.07
    POSITIVE LOGITS
    ousal
    0.27
    ousing
    0.19
    ouses
    0.17
    oused
    0.17
    ouse
    0.15
    ous
    0.14
    OUSE
    0.12
    OUS
    0.12
    deur
    0.12
    ाउस
    0.10
    Activations Density 0.002%

    No Known Activations