© 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. 31115
    Prev
    Next
    INDEX
    Explanations

    german

    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
    iray
    -0.09
     bore
    -0.09
     cud
    -0.09
     rhetoric
    -0.08
    �
    -0.08
     Malawi
    -0.07
     glimps
    -0.07
     rins
    -0.07
     scall
    -0.07
     amp
    -0.07
    POSITIVE LOGITS
    -speaking
    0.10
     uml
    0.09
    ials
    0.09
     مي
    0.08
    aceous
    0.08
     wegen
    0.08
     Germany
    0.08
     Nederlands
    0.08
    Germany
    0.08
     Bundest
    0.08
    Activations Density 0.014%

    No Known Activations