© 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. 21451
    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
     depletion
    -0.09
     depleted
    -0.08
    pletion
    -0.08
    กับ
    -0.08
    ви
    -0.08
     จาก
    -0.08
     אתה
    -0.07
    pleted
    -0.07
     करीब
    -0.07
    是在
    -0.07
    POSITIVE LOGITS
     haghaidh
    0.09
     aapp
    0.09
    ROPERTY
    0.08
    /Image
    0.08
     smo
    0.08
    INSERT
    0.08
    OKEN
    0.08
    SECRET
    0.08
    Funciones
    0.08
     ولكنه
    0.08
    Activations Density 0.000%

    No Known Activations