Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130784
    Prev
    Next
    INDEX
    Explanations

    scent/smell

    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
     планш
    -0.08
    TLS
    -0.08
     stitches
    -0.08
     വിദ്യാഭ്യാസ
    -0.08
     TLS
    -0.08
     Zusch
    -0.07
     pendidikan
    -0.07
    _tls
    -0.07
    tls
    -0.07
    一卡
    -0.07
    POSITIVE LOGITS
     scent
    0.44
     запах
    0.42
     scents
    0.42
     aroma
    0.42
     fragrance
    0.41
     smell
    0.40
     odor
    0.40
     odors
    0.39
     aromas
    0.39
     geur
    0.39
    Activations Density 0.161%

    No Known Activations