© 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. 102207
    Prev
    Next
    INDEX
    Explanations

    line

    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
     bargains
    -0.09
    hethe
    -0.09
     =",
    -0.09
     سپس
    -0.08
    rawdę
    -0.08
     here's
    -0.08
    aveni
    -0.08
     hafði
    -0.08
     hott
    -0.08
     forcibly
    -0.08
    POSITIVE LOGITS
    ↵
    0.09
     विभिन्न
    0.08
    0.08
     berbagai
    0.08
     various
    0.08
     различные
    0.08
    0.07
     km
    0.07
    各种
    0.07
     aligned
    0.07
    Activations Density 0.000%

    No Known Activations