© 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. 44483
    Prev
    Next
    INDEX
    Explanations

    vocal harmonies

    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
     זמן
    -0.08
    .(
    -0.08
    .,
    -0.08
     locom
    -0.08
     consumed
    -0.08
     priced
    -0.08
     مدى
    -0.08
     બજ
    -0.07
     marijuana
    -0.07
    .bias
    -0.07
    POSITIVE LOGITS
     choir
    0.15
     vocals
    0.15
     singing
    0.15
    唱
    0.14
     Singing
    0.13
     chorus
    0.12
     Choir
    0.12
     vocal
    0.12
    歌
    0.12
     singers
    0.11
    Activations Density 0.036%

    No Known Activations