© 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. 51201
    Prev
    Next
    INDEX
    Explanations

    seat

    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
    ઝ
    -0.08
    旬
    -0.08
    رسل
    -0.08
     Sent
    -0.08
     piedi
    -0.08
    께
    -0.08
     sentidos
    -0.08
     Monat
    -0.07
    sent
    -0.07
    asaan
    -0.07
    POSITIVE LOGITS
    belt
    0.19
    bel
    0.14
     belt
    0.13
     occupant
    0.13
    Geek
    0.13
    ings
    0.12
    安排
    0.12
     upholstery
    0.12
    occupied
    0.12
     reservation
    0.12
    Activations Density 0.025%

    No Known Activations