© 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. 11-RESID-POST-AA
    11. 110381
    Prev
    Next
    INDEX
    Explanations

    head

    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
    (?)
    -0.08
     kid
    -0.08
     slaves
    -0.07
    ??↵
    -0.07
    ??↵↵
    -0.07
     foo
    -0.07
     Casas
    -0.07
     fast
    -0.07
    ordin
    -0.07
     Vul
    -0.07
    POSITIVE LOGITS
     fungerar
    0.10
    ંપની
    0.09
    먼
    0.08
     könne
    0.08
     Moż
    0.08
    ટ
    0.08
     verzamelen
    0.08
     주요
    0.08
     meðal
    0.08
    בע
    0.08
    Activations Density 0.072%

    No Known Activations