© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 50731
    Prev
    Next
    INDEX
    Explanations

    benchmark results

    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
     העבודה
    -0.11
     শিক্ষক
    -0.09
     touchscreen
    -0.09
    教師
    -0.09
    教育
    -0.09
     enseignants
    -0.09
     educators
    -0.08
     образователь
    -0.08
     pédagogique
    -0.08
    教师
    -0.08
    POSITIVE LOGITS
     demanding
    0.10
    108
    0.10
     Direct
    0.10
     Dem
    0.09
     titles
    0.09
     Urban
    0.09
     benchmarks
    0.09
     AAA
    0.09
     Shadow
    0.09
     urban
    0.08
    Activations Density 0.005%

    No Known Activations