© 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. 68942
    Prev
    Next
    INDEX
    Explanations

    Permissions and prizes

    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
    beds
    -0.08
     studying
    -0.08
     threats
    -0.08
    чит
    -0.07
     guerr
    -0.07
     numero
    -0.07
     amenazas
    -0.07
     struggles
    -0.07
    �
    -0.07
    治
    -0.07
    POSITIVE LOGITS
     যুক্ত
    0.08
     জ
    0.08
     Animals
    0.08
     animale
    0.07
     Renn
    0.07
    xee
    0.07
    Animals
    0.07
     يكون
    0.07
     జ
    0.07
     attraktive
    0.07
    Activations Density 0.001%

    No Known Activations