© 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. 71098
    Prev
    Next
    INDEX
    Explanations

    public comment

    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
    kind
    -0.08
    -0.08
    Kind
    -0.08
    ь
    -0.07
     cashback
    -0.07
     proficiency
    -0.07
    Driver
    -0.07
    кин
    -0.07
    �
    -0.07
    bitrary
    -0.07
    POSITIVE LOGITS
    意见
    0.11
     hearings
    0.11
    ความคิดเห็น
    0.10
     docket
    0.10
     пікір
    0.10
     petitions
    0.10
     의견
    0.10
     brochure
    0.10
     participaron
    0.09
     Petition
    0.09
    Activations Density 0.052%
    No Known Activations