© 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. 19-RESID-POST-AA
    11. 103509
    Prev
    Next
    INDEX
    Explanations

    cost

    np_max-act-logits · gemini-2.0-flash
    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
     complicado
    -0.09
    decorate
    -0.09
     inconvenient
    -0.08
     troublesome
    -0.08
     troubling
    -0.08
     intricate
    -0.08
     pesky
    -0.08
     μεγάλο
    -0.08
    iculously
    -0.08
     entour
    -0.07
    POSITIVE LOGITS
     savings
    0.36
     Savings
    0.30
    Savings
    0.29
     saving
    0.27
     बच
    0.26
     saved
    0.25
     બચ
    0.25
     ahorro
    0.25
    _saved
    0.24
    Saving
    0.24
    Activations Density 0.008%

    No Known Activations