© 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. 3-RESID-POST-AA
    11. 2807
    Prev
    Next
    INDEX
    Explanations

    json

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	password
    -0.08
     pottery
    -0.08
    碰
    -0.08
     нож
    -0.08
    omatic
    -0.07
     pile
    -0.07
    .stdin
    -0.07
     Peugeot
    -0.07
    -century
    -0.07
    Pizza
    -0.07
    POSITIVE LOGITS
     лиш
    0.08
     Raj
    0.08
     apolog
    0.08
    agd
    0.08
     mise
    0.07
    ({'
    0.07
    शी
    0.07
    ari
    0.07
    ici
    0.07
     afect
    0.07
    Activations Density 0.006%

    No Known Activations