© 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. 71011
    Prev
    Next
    INDEX
    Explanations

    infection

    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
     backbone
    -0.08
    bouwen
    -0.08
    र्ड
    -0.08
     anomal
    -0.07
    ованных
    -0.07
    शनल
    -0.07
    ात्मक
    -0.07
     superior
    -0.07
    سیون
    -0.07
    POSITIVE LOGITS
     nghe
    0.08
    693
    0.08
     pleasurable
    0.08
    	utils
    0.08
    utils
    0.08
     biết
    0.08
     enjoyment
    0.08
     사람이
    0.08
    685
    0.08
     erfahren
    0.08
    Activations Density 0.007%

    No Known Activations