© 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. 63753
    Prev
    Next
    INDEX
    Explanations

    shell commands

    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
     peligros
    -0.09
     personales
    -0.09
     Sentinel
    -0.07
     עובד
    -0.07
    	Task
    -0.07
    ngeles
    -0.07
     gestalt
    -0.07
     Werden
    -0.07
     Vorsitz
    -0.07
     einstakling
    -0.07
    POSITIVE LOGITS
    ाला
    0.09
    ासाठी
    0.08
     IGN
    0.08
     खोल
    0.08
    ड़ी
    0.08
     stump
    0.07
    ाची
    0.07
     insulation
    0.07
    之后
    0.07
     abriu
    0.07
    Activations Density 0.001%

    No Known Activations