© 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 EvalsExportsAPI 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. 112590
    Prev
    Next
    INDEX
    Explanations

    polynomial

    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
     protr
    -0.08
    87
    -0.08
    زاء
    -0.07
    -o
    -0.07
     combustible
    -0.07
    ｲ
    -0.07
     jb
    -0.07
     अंदर
    -0.07
     premi
    -0.07
    台
    -0.07
    POSITIVE LOGITS
    chten
    0.08
    จัก
    0.08
    hrases
    0.08
    ಿಕ್ಕ
    0.07
     soient
    0.07
    handel
    0.07
    Multiplicity
    0.07
     eindeutig
    0.07
    hrase
    0.07
     Duchess
    0.07
    Activations Density 0.004%

    No Known Activations