© 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. 52026
    Prev
    Next
    INDEX
    Explanations

    voltage

    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
    Negative Logits
     parç
    -0.08
    Pisc
    -0.08
    animated
    -0.08
    Lucky
    -0.08
    吞
    -0.07
     STYLE
    -0.07
    Aqu
    -0.07
     Snyder
    -0.07
     fibra
    -0.07
     lucky
    -0.07
    POSITIVE LOGITS
     voltage
    0.37
     potentials
    0.32
    _voltage
    0.31
     potential
    0.31
     Voltage
    0.30
    Voltage
    0.30
     volts
    0.29
     volt
    0.29
     Potential
    0.28
     potentiel
    0.28
    Activations Density 0.044%

    No Known Activations