© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47613
    Prev
    Next
    INDEX
    Explanations

    Arabic text

    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
     lift
    -0.08
     to
    -0.08
     swoje
    -0.07
     lute
    -0.07
     ir
    -0.07
    -l
    -0.07
    Lift
    -0.07
     where
    -0.07
    Lu
    -0.07
     infinity
    -0.07
    POSITIVE LOGITS
     بال
    0.33
     بـ
    0.32
     به
    0.31
     بالم
    0.30
     بت
    0.29
     بالح
    0.29
     بتح
    0.28
     بالأ
    0.28
     بالت
    0.28
     بأ
    0.28
    Activations Density 0.024%

    No Known Activations