© 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. 112363
    Prev
    Next
    INDEX
    Explanations

    ideologies

    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
    vamos
    -0.09
    루
    -0.08
     deserved
    -0.08
    털
    -0.08
    tà
    -0.08
     friendship
    -0.07
    unlikely
    -0.07
    ю
    -0.07
     underestimated
    -0.07
     tubes
    -0.07
    POSITIVE LOGITS
    에서는
    0.10
     zeichnet
    0.10
    では
    0.10
    通常
    0.10
    强调
    0.09
     uuden
    0.09
    主要
    0.08
     hallmark
    0.08
     verfol
    0.08
    核心
    0.08
    Activations Density 0.091%

    No Known Activations