© 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. 114245
    Prev
    Next
    INDEX
    Explanations

    "¿"

    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
    �
    -0.09
     assin
    -0.08
     labyrinth
    -0.08
     의
    -0.08
     애
    -0.07
     Plains
    -0.07
    anns
    -0.07
     Lone
    -0.07
     addu
    -0.07
     abges
    -0.07
    POSITIVE LOGITS
    Qué
    0.09
     consequent
    0.07
    Cómo
    0.07
    nonce
    0.07
     Liga
    0.07
    ər
    0.07
    �
    0.07
    Trans
    0.07
    Dónde
    0.07
    дают
    0.07
    Activations Density 0.002%

    No Known Activations