© 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. 69900
    Prev
    Next
    INDEX
    Explanations

    medical oxygen support

    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
     spreadsheets
    -0.09
    handles
    -0.08
     handles
    -0.08
     Worksheets
    -0.08
    iadau
    -0.08
    ernooi
    -0.08
    nia
    -0.08
     ethereum
    -0.08
     wär
    -0.08
    artner
    -0.08
    POSITIVE LOGITS
    From
    0.07
     entro
    0.07
     saline
    0.07
     mounting
    0.07
     Kings
    0.07
    .Small
    0.07
    Ba
    0.07
     equilibrium
    0.07
    (m
    0.07
     From
    0.07
    Activations Density 0.001%

    No Known Activations