© 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. 50964
    Prev
    Next
    INDEX
    Explanations

    s

    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
     carbohydrates
    -0.09
     Metals
    -0.08
     metals
    -0.08
    イン
    -0.08
     portas
    -0.08
     carbs
    -0.08
     weaknesses
    -0.08
     vagas
    -0.08
     المعادن
    -0.08
    raagt
    -0.08
    POSITIVE LOGITS
    ycles
    0.12
    yles
    0.10
    prints
    0.09
    print
    0.09
    yek
    0.09
     print
    0.09
    ér
    0.08
    ycle
    0.08
     Er
    0.08
    yl
    0.08
    Activations Density 0.001%

    No Known Activations