© 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. 69919
    Prev
    Next
    INDEX
    Explanations

    ice cream/gelato

    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
     meditate
    -0.08
    Compliance
    -0.08
     Resume
    -0.07
     Compliance
    -0.07
     Meets
    -0.07
    -template
    -0.07
    력이
    -0.07
    _ALIGNMENT
    -0.07
    aleo
    -0.07
    edit
    -0.07
    POSITIVE LOGITS
     enjoyable
    0.10
     vendors
    0.09
     vendor
    0.09
     vending
    0.09
     genießen
    0.09
     amusement
    0.08
     kios
    0.08
     profiter
    0.08
     pedestrian
    0.08
    .choice
    0.08
    Activations Density 0.011%

    No Known Activations