© 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. 114259
    Prev
    Next
    INDEX
    Explanations

    advertisements

    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
    编码
    -0.08
    ศึกษา
    -0.08
    iameter
    -0.08
     연구
    -0.08
     Cod
    -0.08
     Somit
    -0.07
     Ledger
    -0.07
     Prü
    -0.07
    .Code
    -0.07
     Brow
    -0.07
    POSITIVE LOGITS
     encourages
    0.14
     urges
    0.13
     urging
    0.13
     urged
    0.13
     offerings
    0.12
     encourage
    0.12
     enticing
    0.12
     encouraging
    0.12
     aanbiedingen
    0.12
     advertise
    0.11
    Activations Density 0.325%

    No Known Activations