© 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. 23-RESID-POST-AA
    11. 48772
    Prev
    Next
    INDEX
    Explanations

    semiconductor fabrication processes

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     levens
    -0.09
     život
    -0.08
     სულ
    -0.08
    ukhulu
    -0.08
    oleč
    -0.08
     ذریع
    -0.08
     élet
    -0.08
     деді
    -0.08
     زندگي
    -0.08
     উপজেলার
    -0.08
    POSITIVE LOGITS
    Fin
    0.13
     Fin
    0.13
    28
    0.09
    arme
    0.09
    .fin
    0.09
     fin
    0.09
    fin
    0.09
     Arm
    0.08
     transistor
    0.08
     carbide
    0.08
    Activations Density 0.009%

    No Known Activations