© 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. 19235
    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
    ไหนดี
    -0.08
     金砖
    -0.08
     மெ
    -0.08
    ნელ
    -0.08
    සර
    -0.08
    կար
    -0.08
     ниндәй
    -0.08
    "`
    -0.08
    astricht
    -0.08
     метро
    -0.08
    POSITIVE LOGITS
    self
    0.08
     begs
    0.08
    Susan
    0.08
    	self
    0.08
     Thoughts
    0.07
    .Dock
    0.07
    優
    0.07
     thoughts
    0.07
     truy
    0.07
     self
    0.07
    Activations Density 0.000%

    No Known Activations