© 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. 50661
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
     sidoo
    -0.09
    ‌ای
    -0.08
     preceding
    -0.08
    uerdo
    -0.08
     hefyd
    -0.08
     ასევე
    -0.08
     پڻ
    -0.08
    iós
    -0.08
     დაამ
    -0.08
    벤트
    -0.08
    POSITIVE LOGITS
     ambos
    0.12
    第三
    0.12
     दोनों
    0.12
     Both
    0.12
     third
    0.12
    Third
    0.12
    third
    0.11
     બંને
    0.11
     Ambos
    0.11
     Beide
    0.11
    Activations Density 0.112%

    No Known Activations