© 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. 103600
    Prev
    Next
    INDEX
    Explanations

    android

    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
    essoa
    -0.08
     greater
    -0.08
    enne
    -0.08
     Conce
    -0.08
    ereum
    -0.07
    ailed
    -0.07
     celebra
    -0.07
     were
    -0.07
    schuld
    -0.07
     उल्ल
    -0.07
    POSITIVE LOGITS
    :id
    0.13
    _id
    0.11
    	id
    0.11
    	ID
    0.10
    (id
    0.10
    .translates
    0.09
     id
    0.09
    	if
    0.08
    'id
    0.08
    {id
    0.08
    Activations Density 0.001%

    No Known Activations