© 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. 63168
    Prev
    Next
    INDEX
    Explanations

    hospice

    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
     tile
    -0.08
     sheet
    -0.08
     Islands
    -0.07
     encima
    -0.07
     mess
    -0.07
    hell
    -0.07
     sqrt
    -0.07
     Ke
    -0.07
     hole
    -0.07
    IELD
    -0.07
    POSITIVE LOGITS
     hospice
    0.13
     Hospice
    0.12
    alliative
    0.10
    веч
    0.08
     compassionate
    0.08
     decoração
    0.08
     lovingly
    0.08
     Schwangerschaft
    0.08
    edicine
    0.08
     സൗ
    0.08
    Activations Density 0.006%

    No Known Activations