© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 49062
    Prev
    Next
    INDEX
    Explanations

    Code execution directives

    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
     adopter
    -0.08
    (grid
    -0.08
    .compute
    -0.08
     manifests
    -0.08
    .cljs
    -0.08
    ITING
    -0.08
    .grid
    -0.08
    _truth
    -0.08
     amphib
    -0.08
    .dart
    -0.08
    POSITIVE LOGITS
     Exec
    0.15
    Exec
    0.15
     Restart
    0.13
     Directive
    0.12
    Restart
    0.12
    Directive
    0.12
     Options
    0.12
     directive
    0.12
    Listen
    0.12
    .Exec
    0.11
    Activations Density 0.011%

    No Known Activations