© 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. 103303
    Prev
    Next
    INDEX
    Explanations

    escape

    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
    θή
    -0.09
     voller
    -0.08
     redução
    -0.08
     fără
    -0.08
     samma
    -0.08
     hưởng
    -0.08
    без
    -0.08
    Supp
    -0.08
     ohne
    -0.07
     Defined
    -0.07
    POSITIVE LOGITS
     properly
    0.18
     appropriately
    0.18
     correctement
    0.16
     adequately
    0.15
     correctamente
    0.15
     правильно
    0.15
     corretamente
    0.14
     adecu
    0.14
     correctly
    0.14
     oikein
    0.13
    Activations Density 0.009%

    No Known Activations