© 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. 102525
    Prev
    Next
    INDEX
    Explanations

    Let's

    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
     or
    -0.10
     किंवा
    -0.10
     etc
    -0.09
     లేదా
    -0.09
     eller
    -0.09
     или
    -0.09
     olsa
    -0.09
     અથવા
    -0.09
    .Some
    -0.09
     but
    -0.09
    POSITIVE LOGITS
    重新
    0.21
     carefully
    0.21
    再次
    0.21
     correctly
    0.20
     reconsider
    0.20
     വീണ്ടും
    0.20
     다시
    0.20
     ಮತ್ತೆ
    0.20
     ree
    0.19
     ફરી
    0.19
    Activations Density 0.051%

    No Known Activations