© 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. 47812
    Prev
    Next
    INDEX
    Explanations

    say "2"

    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
    .Exception
    -0.08
    عبة
    -0.08
     anomalies
    -0.08
    èm
    -0.08
     NIE
    -0.08
    uelles
    -0.08
    _Exception
    -0.08
    Wie
    -0.08
     Steering
    -0.07
    خرى
    -0.07
    POSITIVE LOGITS
     two
    0.13
    ¾
    0.12
     Two
    0.12
     Mark
    0.12
     Acts
    0.11
    _mark
    0.11
    Acts
    0.11
    _two
    0.11
     Matthew
    0.11
     दोन
    0.11
    Activations Density 0.110%

    No Known Activations