© 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. 43570
    Prev
    Next
    INDEX
    Explanations

    Munich

    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
    279
    -0.08
    bull
    -0.08
     أساس
    -0.07
    -b
    -0.07
     कव
    -0.07
    -this
    -0.07
    andid
    -0.07
    trx
    -0.07
     バ
    -0.07
    -cons
    -0.07
    POSITIVE LOGITS
     спокойно
    0.09
     useless
    0.08
    ’Es
    0.08
     Peace
    0.08
     refugi
    0.08
     peacefully
    0.08
    .Ignore
    0.08
     Junction
    0.08
    @hotmail
    0.08
     gef
    0.08
    Activations Density 0.005%

    No Known Activations