© 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. 96293
    Prev
    Next
    INDEX
    Explanations

    side

    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
    Italian
    -0.11
    heartbeat
    -0.11
    episodes
    -0.11
    articles
    -0.10
    כתוב
    -0.10
    samples
    -0.10
    float
    -0.10
    errors
    -0.10
    Portugu
    -0.10
    menus
    -0.10
    POSITIVE LOGITS
    (s
    0.16
     containing
    0.15
     involving
    0.15
     consisting
    0.14
     of
    0.13
    -wise
    0.13
     comprising
    0.12
     '
    0.12
     pertaining
    0.12
     содержащ
    0.12
    Activations Density 0.081%

    No Known Activations