© 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. 23-RESID-POST-AA
    11. 50513
    Prev
    Next
    INDEX
    Explanations

    adjectives

    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
     Tech
    -0.14
     meds
    -0.12
     Specials
    -0.11
     originals
    -0.11
     Clinics
    -0.11
     Labs
    -0.11
     Injury
    -0.11
     Therapy
    -0.10
     Rehab
    -0.10
     Surgery
    -0.10
    POSITIVE LOGITS
     contemporary
    0.15
     residential
    0.14
     terrestrial
    0.13
     modern
    0.13
     commercial
    0.13
     mainstream
    0.12
     conventional
    0.12
     civilian
    0.12
     recreational
    0.12
     traditional
    0.12
    Activations Density 0.274%

    No Known Activations