© 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 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. 31162
    Prev
    Next
    INDEX
    Explanations

    reading to children

    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
    ivne
    -0.09
     sildenafil
    -0.09
     skyline
    -0.08
    асці
    -0.08
     BMX
    -0.08
     экст
    -0.08
     krv
    -0.08
    축
    -0.08
    _tracker
    -0.08
     testoster
    -0.08
    POSITIVE LOGITS
     bedtime
    0.11
     aloud
    0.11
     cuentos
    0.10
     storytelling
    0.09
    讲
    0.09
     Books
    0.09
    Books
    0.08
     luisteren
    0.08
     reading
    0.08
     exchanging
    0.08
    Activations Density 0.020%

    No Known Activations