© 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. 114038
    Prev
    Next
    INDEX
    Explanations

    human rights

    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
    টার
    -0.08
    yectos
    -0.08
     versions
    -0.08
    minton
    -0.08
    Spain
    -0.08
     referred
    -0.08
    autions
    -0.07
     asynchronous
    -0.07
    versions
    -0.07
    fyn
    -0.07
    POSITIVE LOGITS
     herkes
    0.10
     Amnesty
    0.09
     am
    0.09
     arz
    0.09
     everyone
    0.09
     Everyone
    0.08
     ruk
    0.08
     حقوق
    0.08
     Rights
    0.08
     entitlement
    0.08
    Activations Density 0.008%

    No Known Activations