© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 96347
    Prev
    Next
    INDEX
    Explanations

    code

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trav
    -0.09
     Adv
    -0.07
    Pick
    -0.07
     Cr
    -0.07
    ுந்த
    -0.07
     Pick
    -0.07
     Trav
    -0.07
    cr
    -0.07
    _pick
    -0.07
    fw
    -0.07
    POSITIVE LOGITS
    ерх
    0.09
    	parameters
    0.09
     rote
    0.08
    unks
    0.08
    esse
    0.08
     infrastructures
    0.08
     Andreas
    0.08
    ిణ
    0.08
    дики
    0.08
     әң
    0.08
    Activations Density 0.000%

    No Known Activations