© 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. 69216
    Prev
    Next
    INDEX
    Explanations

    fingers

    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
     lhe
    -0.09
     bekeken
    -0.08
    atri
    -0.08
     barking
    -0.08
    Works
    -0.08
    觀看
    -0.08
    Neo
    -0.08
     gait
    -0.08
     barefoot
    -0.08
    kontakte
    -0.08
    POSITIVE LOGITS
     Ef
    0.08
     슬롯
    0.08
     Slots
    0.08
     Coll
    0.07
     Savings
    0.07
     Slot
    0.07
     Syndrome
    0.07
    _POSITION
    0.07
     אס
    0.07
     Expect
    0.07
    Activations Density 0.002%

    No Known Activations