© 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. 21790
    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
     ഉട
    -0.09
     Ownership
    -0.09
    'user
    -0.09
    атков
    -0.08
     Owners
    -0.08
     owners
    -0.08
    	Public
    -0.08
     പ്രമുഖ
    -0.08
     Voices
    -0.08
    Taste
    -0.08
    POSITIVE LOGITS
     rectangle
    0.19
    _rectangle
    0.18
    rectangle
    0.18
     ellipse
    0.17
    Rectangle
    0.17
     triangle
    0.17
     rectangular
    0.17
    .rectangle
    0.17
     cylinder
    0.16
    ellipse
    0.16
    Activations Density 0.071%

    No Known Activations