© 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. 20803
    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
    rored
    -0.08
     ہمار
    -0.08
     access
    -0.08
    thel
    -0.08
    ":{↵
    -0.08
     our
    -0.08
     ".↵
    -0.08
    ':[
    -0.08
    。",↵
    -0.08
    ibat
    -0.08
    POSITIVE LOGITS
    .unwrap
    0.08
     //
    0.08
    .subtract
    0.08
     =
    0.08
    ,
    0.08
    .solve
    0.08
    .clear
    0.08
     /=
    0.08
     *
    0.08
     beiden
    0.08
    Activations Density 0.025%

    No Known Activations