© 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. 23-RESID-POST-AA
    11. 50786
    Prev
    Next
    INDEX
    Explanations

    say "Start" or "Aw" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destroy
    -0.13
    (create
    -0.13
    (remove
    -0.12
     replace
    -0.12
    (update
    -0.12
    remove
    -0.12
    (compare
    -0.11
     add
    -0.11
    	remove
    -0.11
     discard
    -0.11
    POSITIVE LOGITS
     On
    0.21
    	On
    0.18
     Awake
    0.16
     Try
    0.15
    (On
    0.15
     Initialize
    0.15
    .On
    0.15
    On
    0.15
     Late
    0.14
     Start
    0.14
    Activations Density 0.009%

    No Known Activations