© 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. 68609
    Prev
    Next
    INDEX
    Explanations

    tempered

    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
     batang
    -0.08
     consc
    -0.08
    ocrats
    -0.08
    婆
    -0.08
     preco
    -0.08
    未经
    -0.07
     diter
    -0.07
     percentual
    -0.07
     irres
    -0.07
     sacerd
    -0.07
    POSITIVE LOGITS
    (errno
    0.08
     Davies
    0.08
     Gewalt
    0.08
    izen
    0.08
     Aspect
    0.07
    kill
    0.07
    Ey
    0.07
     Ey
    0.07
    Dav
    0.07
     risico
    0.07
    Activations Density 0.009%

    No Known Activations