© 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. 71047
    Prev
    Next
    INDEX
    Explanations

    multitasking

    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
    ahn
    -0.08
     relative
    -0.07
    ]],
    -0.07
    ]]
    -0.07
     κοιν
    -0.07
    .Initial
    -0.07
    ]]↵
    -0.07
    ोद
    -0.07
     dispoz
    -0.07
     uml
    -0.07
    POSITIVE LOGITS
     multit
    0.14
     belast
    0.10
    -task
    0.10
     inatt
    0.09
     못
    0.09
    autocomplete
    0.09
    _MULTI
    0.08
     distractions
    0.08
     переключ
    0.08
     distracted
    0.08
    Activations Density 0.016%

    No Known Activations