© 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. 110427
    Prev
    Next
    INDEX
    Explanations

    Kuiper Belt

    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
     TRY
    -0.10
     Welding
    -0.09
     mortar
    -0.08
    breadcrumbs
    -0.08
     bread
    -0.08
     trying
    -0.08
     welding
    -0.08
    _try
    -0.08
     Trying
    -0.08
    消防
    -0.08
    POSITIVE LOGITS
     twilight
    0.11
     Voyager
    0.10
     sea
    0.09
     समुद
    0.09
     Fringe
    0.09
     ontde
    0.09
     fringe
    0.09
    Sea
    0.09
    osphere
    0.09
     ontdekt
    0.08
    Activations Density 0.005%

    No Known Activations