© 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. 22559
    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
     any
    -0.10
    ​របស់
    -0.09
     তৈরি
    -0.09
     cualquier
    -0.09
     twor
    -0.08
     erstellt
    -0.08
     create
    -0.08
     разработ
    -0.08
     créé
    -0.08
     żad
    -0.08
    POSITIVE LOGITS
    'x
    0.08
    Are
    0.08
     उसने
    0.08
    aughter
    0.08
    xtap
    0.08
    inderung
    0.08
    _are
    0.08
    آخر
    0.08
    اتو
    0.07
    IFO
    0.07
    Activations Density 0.000%

    No Known Activations