© 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. 19-RESID-POST-AA
    11. 21082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     escult
    -0.08
    ট্টগ্র
    -0.08
    מס
    -0.08
    אג
    -0.08
    ngine
    -0.08
    obao
    -0.08
     atrações
    -0.07
    Arithmetic
    -0.07
    	msg
    -0.07
    endaji
    -0.07
    POSITIVE LOGITS
     credentials
    0.34
    credentials
    0.30
    _credentials
    0.29
    Credentials
    0.29
     Credentials
    0.28
     Zugang
    0.28
     access
    0.27
    .credentials
    0.27
    _ACCESS
    0.24
     accès
    0.24
    Activations Density 0.024%

    No Known Activations