© 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. 129148
    Prev
    Next
    INDEX
    Explanations

    Electricity

    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
     coached
    -0.08
     stile
    -0.08
     стоп
    -0.08
    鲸
    -0.08
     metav
    -0.08
     masses
    -0.07
     oro
    -0.07
     taxa
    -0.07
     trouw
    -0.07
     pyramid
    -0.07
    POSITIVE LOGITS
     electrical
    0.22
     الكهربائية
    0.21
     électrique
    0.20
     electricity
    0.20
     listrik
    0.20
     électriques
    0.20
     Electrical
    0.19
     eléctrica
    0.19
    Electrical
    0.19
     elétrica
    0.19
    Activations Density 0.084%

    No Known Activations