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

    Neuronpedia

    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. 99880
    Prev
    Next
    INDEX
    Explanations

    Article beginnings

    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
    upe
    -0.09
     
    -0.08
     sait
    -0.08
     portugueses
    -0.08
    algo
    -0.07
    咪
    -0.07
    htable
    -0.07
    todo
    -0.07
     Abel
    -0.07
    pf
    -0.07
    POSITIVE LOGITS
     �
    0.10
     inkl
    0.08
     Gle
    0.07
    cil
    0.07
    advert
    0.07
     drills
    0.07
     Continua
    0.07
     Bac
    0.07
     Herd
    0.07
     priorit
    0.07
    Activations Density 0.260%

    No Known Activations