© 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. 113134
    Prev
    Next
    INDEX
    Explanations

    German text

    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
     Harris
    -0.08
     Crane
    -0.08
     ramp
    -0.08
     cranes
    -0.08
     ramps
    -0.08
     fundador
    -0.07
     mice
    -0.07
    'fh
    -0.07
    NFL
    -0.07
    rift
    -0.07
    POSITIVE LOGITS
     ગુજરાતી
    0.08
     multilingual
    0.08
     中文
    0.08
     বাংলা
    0.08
     kar
    0.08
    sanitize
    0.08
     masz
    0.07
    います
    0.07
    urat
    0.07
     বাংল
    0.07
    Activations Density 0.009%

    No Known Activations