© 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. 937
    Prev
    Next
    INDEX
    Explanations

    larceny or theft

    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
     Fab
    -0.09
     сез
    -0.08
     próximas
    -0.08
    ிருந்த
    -0.08
     Vit
    -0.08
     platinum
    -0.08
     Kul
    -0.07
     Kult
    -0.07
     Aloe
    -0.07
     wheat
    -0.07
    POSITIVE LOGITS
     perpetr
    0.09
    กรรม
    0.08
    _SINGLE
    0.08
    _complete
    0.08
     monument
    0.08
     dog
    0.07
    commodity
    0.07
     jedn
    0.07
     pornography
    0.07
    /property
    0.07
    Activations Density 0.005%

    No Known Activations