© 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 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. 112719
    Prev
    Next
    INDEX
    Explanations

    ence

    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
    員
    -0.08
     Zusammenhang
    -0.08
    nehmen
    -0.08
     deut
    -0.08
     parasites
    -0.08
    gegeben
    -0.08
     glatt
    -0.07
     Jonas
    -0.07
     Pach
    -0.07
    忙
    -0.07
    POSITIVE LOGITS
     Renaissance
    0.08
     photoc
    0.08
    Flower
    0.08
    0.08
    Alg
    0.08
     scars
    0.08
    Paperback
    0.08
     thou
    0.08
    Bos
    0.07
    AGO
    0.07
    Activations Density 0.007%
    No Known Activations