© 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. 11-RESID-POST-AA
    11. 70288
    Prev
    Next
    INDEX
    Explanations

    definitions and contradictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gay
    -0.08
     going
    -0.07
     collaboratively
    -0.07
    еша
    -0.07
     interviewer
    -0.07
    -rec
    -0.07
     securely
    -0.07
     Freddie
    -0.07
    .fix
    -0.07
    ങ്ങി
    -0.07
    POSITIVE LOGITS
     mmet
    0.09
     ntụ
    0.08
     सैन
    0.08
    obian
    0.08
    ுப்ப
    0.08
     бол
    0.08
    דר
    0.08
     ವರ್�
    0.07
    	aux
    0.07
    ייַט
    0.07
    Activations Density 0.000%

    No Known Activations