© 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. 69679
    Prev
    Next
    INDEX
    Explanations

    Code documentation

    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
     powerhouse
    -0.08
    Beat
    -0.08
    춤
    -0.08
    ofia
    -0.08
     adjustable
    -0.07
     dalam
    -0.07
     tun
    -0.07
    打
    -0.07
     emot
    -0.07
     Coastal
    -0.07
    POSITIVE LOGITS
     garantiert
    0.12
     garantit
    0.12
     Guarante
    0.12
     upheld
    0.11
     гарант
    0.11
     garantiza
    0.11
     guarantees
    0.11
     forall
    0.11
     invari
    0.11
     integrity
    0.10
    Activations Density 0.006%

    No Known Activations