© 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. 68419
    Prev
    Next
    INDEX
    Explanations

    blank lines and newlines

    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
     tinta
    -0.09
    _chr
    -0.09
    ilir
    -0.08
     he'd
    -0.08
     '</
    -0.08
     he's
    -0.08
    .Bounds
    -0.07
     అంట
    -0.07
    incia
    -0.07
    jati
    -0.07
    POSITIVE LOGITS
     grac
    0.08
    amn
    0.07
    സ്സ
    0.07
     छात्र
    0.07
    especially
    0.07
    �
    0.07
     ๆ
    0.07
    (deck
    0.07
    學生
    0.07
    々
    0.06
    Activations Density 0.001%

    No Known Activations