© 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. 18400
    Prev
    Next
    INDEX
    Explanations

    socket

    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
     trituradora
    -0.08
    Tritur
    -0.08
     DBNull
    -0.08
     trituración
    -0.08
     Macbeth
    -0.08
    άρ
    -0.07
     hairy
    -0.07
    æs
    -0.07
    _ARM
    -0.07
     wicker
    -0.07
    POSITIVE LOGITS
     Socket
    0.23
    .socket
    0.20
     socket
    0.20
    Socket
    0.20
    .Socket
    0.20
    	socket
    0.19
    (Socket
    0.19
    _socket
    0.19
    (socket
    0.19
    .io
    0.19
    Activations Density 0.002%

    No Known Activations