© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 99512
    Prev
    Next
    INDEX
    Explanations

    compound

    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
     할
    -0.08
     bipolar
    -0.08
    walker
    -0.08
    jt
    -0.08
    -0.08
     curated
    -0.07
    koord
    -0.07
     Francesco
    -0.07
     왜
    -0.07
     oeuvre
    -0.07
    POSITIVE LOGITS
     compounded
    0.10
     diária
    0.09
     quarterly
    0.08
     juros
    0.08
     intervals
    0.08
     groundwater
    0.08
     mensal
    0.08
     impuestos
    0.08
     monthly
    0.08
     taxes
    0.08
    Activations Density 0.004%
    No Known Activations