Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44272
    Prev
    Next
    INDEX
    Explanations

    %

    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
     licensing
    -0.08
     ged
    -0.08
     mense
    -0.08
     policing
    -0.07
     Patri
    -0.07
     Memor
    -0.07
     pate
    -0.07
    طق
    -0.07
    irling
    -0.07
     koristi
    -0.07
    POSITIVE LOGITS
     spp
    0.08
     sugars
    0.07
    сон
    0.07
    ров
    0.07
     gson
    0.07
     carbohydrates
    0.07
     sapien
    0.07
     preferably
    0.07
    ajad
    0.07
     javafx
    0.07
    Activations Density 0.003%

    No Known Activations