© 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. 7-RESID-POST-AA
    11. 977
    Prev
    Next
    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asta
    -0.08
    이에
    -0.07
     дома
    -0.07
    Landing
    -0.07
    �
    -0.07
    Landscape
    -0.07
     Andrade
    -0.07
    Vitals
    -0.07
     വാർത്ത
    -0.07
     BM
    -0.07
    POSITIVE LOGITS
     cruc
    0.08
     Disability
    0.08
    isse
    0.07
     Derrick
    0.07
    itum
    0.07
     contrário
    0.07
     Alm
    0.07
     Hunts
    0.07
    084
    0.07
     pinnacle
    0.07
    Activations Density 0.013%

    No Known Activations