© 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. 68638
    Prev
    Next
    INDEX
    Explanations

    am/fm radio

    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
     Ballet
    -0.09
    imshow
    -0.08
     ballet
    -0.08
     kore
    -0.08
     zdję
    -0.08
     clothes
    -0.08
     kê
    -0.08
    衣
    -0.08
    czema
    -0.07
     zagen
    -0.07
    POSITIVE LOGITS
     luisteren
    0.09
     listened
    0.09
    电话
    0.09
     headphones
    0.08
     écouter
    0.08
    響
    0.08
     laut
    0.08
     listeners
    0.08
     sistemas
    0.08
     hören
    0.07
    Activations Density 0.126%

    No Known Activations