© 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. 26154
    Prev
    Next
    INDEX
    Explanations

    tracking

    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
    फल
    -0.08
     Fried
    -0.08
    lob
    -0.08
     leftover
    -0.08
    ments
    -0.08
     höf
    -0.08
     club
    -0.08
     población
    -0.08
     creamy
    -0.08
    余
    -0.07
    POSITIVE LOGITS
    orras
    0.08
     Enable
    0.08
     tracing
    0.08
    ABILITY
    0.07
     justiça
    0.07
    abilities
    0.07
    െത്ത
    0.07
     justice
    0.07
    enable
    0.07
    Ability
    0.07
    Activations Density 0.003%

    No Known Activations