© 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. 19-RESID-POST-AA
    11. 19844
    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
     tasting
    -0.12
     baptism
    -0.12
     FTP
    -0.12
    Cake
    -0.12
     ftp
    -0.11
    smtp
    -0.11
    ftp
    -0.11
     Cake
    -0.11
    .smtp
    -0.10
     vowel
    -0.10
    POSITIVE LOGITS
     magnetic
    0.41
     магнит
    0.34
     Magnetic
    0.34
     magnet
    0.32
     magnets
    0.31
    磁
    0.28
     Magnet
    0.27
    agnetic
    0.23
    agnet
    0.21
    mag
    0.20
    Activations Density 0.031%

    No Known Activations