© 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. 11-RESID-POST-AA
    11. 110719
    Prev
    Next
    INDEX
    Explanations

    efficient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    梁
    -0.09
    Gir
    -0.08
     Pon
    -0.08
     prueba
    -0.08
     proven
    -0.07
    lı
    -0.07
     Katherine
    -0.07
    overs
    -0.07
     envis
    -0.07
     ನಮ
    -0.07
    POSITIVE LOGITS
     pang
    0.08
    incs
    0.08
     ós
    0.07
     للغاية
    0.07
    inc
    0.07
    compress
    0.07
    iciency
    0.07
    ertung
    0.07
    sels
    0.07
     tandem
    0.07
    Activations Density 0.014%

    No Known Activations