© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78962
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     Duff
    -0.08
     Chapman
    -0.07
    ’um
    -0.07
     troubling
    -0.07
     الق
    -0.07
    eming
    -0.07
     Ums
    -0.07
     Mur
    -0.07
     Jama
    -0.07
     Neck
    -0.07
    POSITIVE LOGITS
     wl
    0.07
     wildcard
    0.07
     см
    0.07
    cta
    0.07
    民
    0.07
    ocia
    0.07
    helial
    0.07
    оит
    0.07
     nil
    0.07
    ோ
    0.07
    Activations Density 0.039%

    No Known Activations