© 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. 31369
    Prev
    Next
    INDEX
    Explanations

    parenting

    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
     CERN
    -0.09
     accelerator
    -0.09
     Crypto
    -0.08
     крип
    -0.08
     DOS
    -0.08
     Accelerator
    -0.08
     phishing
    -0.08
     Corporation
    -0.08
     Kryptow
    -0.08
     Corridor
    -0.08
    POSITIVE LOGITS
     parenting
    0.18
     pediatric
    0.17
     careg
    0.17
     caregiver
    0.17
     caregivers
    0.17
     Parenting
    0.16
     పిల్ల
    0.16
     Pediatric
    0.16
     குழந்த
    0.15
    儿童
    0.15
    Activations Density 0.137%

    No Known Activations