© 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. 20402
    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
     Basic
    -0.07
    ktr
    -0.07
     Camping
    -0.07
    ôtes
    -0.07
    ahat
    -0.07
     ücretsiz
    -0.07
     campe
    -0.07
    rekking
    -0.07
    osk
    -0.07
     приключ
    -0.06
    POSITIVE LOGITS
     slowly
    0.26
     gradually
    0.25
     lentamente
    0.25
     gradual
    0.24
     langzaam
    0.24
     धीरे
    0.24
     langsam
    0.23
     Slowly
    0.23
     постеп
    0.22
     постепенно
    0.22
    Activations Density 0.015%

    No Known Activations