© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110451
    Prev
    Next
    INDEX
    Explanations

    Legal advice

    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
     Toggle
    -0.10
    .wso
    -0.09
     Maschinen
    -0.09
     ocas
    -0.09
     ambiance
    -0.08
    skap
    -0.08
    _toggle
    -0.08
     Turk
    -0.08
    toggle
    -0.08
    yon
    -0.08
    POSITIVE LOGITS
     litigation
    0.15
     attorney
    0.14
    律师
    0.14
     defendants
    0.13
     attorneys
    0.13
     plaintiffs
    0.13
     subpoena
    0.13
     адв
    0.12
     Litigation
    0.12
     suing
    0.12
    Activations Density 0.092%

    No Known Activations