© 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. 11-RESID-POST-AA
    11. 30341
    Prev
    Next
    INDEX
    Explanations

    water cooling

    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
     Gummies
    -0.08
     effecten
    -0.08
     recreated
    -0.08
    gina
    -0.08
     gint
    -0.08
     summons
    -0.08
     Pill
    -0.08
     cuentas
    -0.08
    lng
    -0.08
     zák
    -0.08
    POSITIVE LOGITS
     охлаж
    0.14
     cooling
    0.13
    Cooling
    0.11
     coolant
    0.11
     Cooling
    0.11
     temperature
    0.10
    Temperature
    0.09
    Heat
    0.09
     ताप
    0.09
     cooled
    0.09
    Activations Density 0.019%

    No Known Activations