© 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. 110848
    Prev
    Next
    INDEX
    Explanations

    bulk database insertion

    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
     installed
    -0.08
     세계
    -0.08
     goggles
    -0.08
     Installed
    -0.08
     imaging
    -0.08
     seventh
    -0.08
     Valve
    -0.08
     ịch
    -0.07
     was
    -0.07
     svět
    -0.07
    POSITIVE LOGITS
     batching
    0.20
    Batch
    0.19
    _BATCH
    0.19
    .batch
    0.19
     batch
    0.18
    _batch
    0.17
    batch
    0.17
     batches
    0.17
    批
    0.17
     Batch
    0.16
    Activations Density 0.009%

    No Known Activations