© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68663
    Prev
    Next
    INDEX
    Explanations

    multi-sensory technology

    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
    贤
    -0.09
     todo
    -0.07
     FIX
    -0.07
     nust
    -0.07
     Suicide
    -0.07
    AGMENT
    -0.07
     interesses
    -0.07
     Layers
    -0.07
     Vargas
    -0.07
     Tier
    -0.07
    POSITIVE LOGITS
     tactile
    0.20
     scents
    0.16
     scent
    0.16
     sensations
    0.15
     geur
    0.13
     smells
    0.13
     sensation
    0.13
     запах
    0.13
     sensory
    0.12
     auditory
    0.12
    Activations Density 0.056%

    No Known Activations