© 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. 45369
    Prev
    Next
    INDEX
    Explanations

    LDAP

    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
     répar
    -0.09
     consequences
    -0.09
     installments
    -0.08
     offspring
    -0.08
     repairs
    -0.08
     consecuencias
    -0.08
     مشکلات
    -0.08
    ляд
    -0.08
     outputs
    -0.08
     réparer
    -0.08
    POSITIVE LOGITS
    Membership
    0.09
    θο
    0.09
    സ
    0.08
    _external
    0.08
    Authenticate
    0.08
    membership
    0.08
    `
↵
    0.08
    cii
    0.08
    സഭ
    0.08
    _EXTERNAL
    0.08
    Activations Density 0.006%

    No Known Activations