© 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. 19-RESID-POST-AA
    11. 22044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (sentence
    -0.09
     flexibility
    -0.08
     flex
    -0.08
     mė
    -0.08
     preci
    -0.08
    礼包
    -0.07
     tradicion
    -0.07
     gil
    -0.07
     tsam
    -0.07
     rectangle
    -0.07
    POSITIVE LOGITS
     Couch
    0.13
    DATABASE
    0.11
     replication
    0.11
     디자인
    0.11
    数据库
    0.10
     couch
    0.10
    database
    0.10
     databases
    0.10
     database
    0.10
    Replication
    0.10
    Activations Density 0.001%

    No Known Activations