© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 22718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विद्य
    -0.09
     bookkeeping
    -0.08
     pels
    -0.08
     Electrical
    -0.08
     मुद्रा
    -0.08
     primitives
    -0.08
    áték
    -0.08
    mites
    -0.08
    �ក
    -0.08
    .Socket
    -0.08
    POSITIVE LOGITS
     chorus
    0.20
     Chorus
    0.15
     rhyme
    0.14
     catchy
    0.13
     lyrics
    0.13
     refrain
    0.13
     verses
    0.12
    歌词
    0.12
     lyric
    0.12
    高潮
    0.11
    Activations Density 0.007%

    No Known Activations