© 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. 19-RESID-POST-AA
    11. 18396
    Prev
    Next
    INDEX
    Explanations

    long

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    recogn
    -0.08
    -France
    -0.08
    -Up
    -0.08
    plattform
    -0.08
    /?
    -0.08
    subjects
    -0.08
    essential
    -0.08
    '){
↵
    -0.08
    -Uni
    -0.07
    ié
    -0.07
    POSITIVE LOGITS
     long
    0.24
    _long
    0.19
    	long
    0.19
     longs
    0.19
    _LONG
    0.18
    Long
    0.18
    long
    0.18
    长
    0.17
     longa
    0.17
     longo
    0.17
    Activations Density 0.001%

    No Known Activations