© 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. 6730
    Prev
    Next
    INDEX
    Explanations

    Prisma

    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
    glyphicon
    -0.09
    _SERV
    -0.09
     glyphicon
    -0.09
    港
    -0.09
    _WIFI
    -0.08
    	gtk
    -0.08
    ্ব
    -0.08
    ชาย
    -0.07
     rospy
    -0.07
    GHz
    -0.07
    POSITIVE LOGITS
     Prisma
    0.20
     prisma
    0.19
     @@
    0.13
     connect
    0.12
     Connect
    0.11
     conect
    0.11
     connecter
    0.11
    Connect
    0.10
    Unchecked
    0.10
    .connect
    0.10
    Activations Density 0.004%

    No Known Activations