© 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. 110816
    Prev
    Next
    INDEX
    Explanations

    Irish language/places

    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
    町
    -0.08
     Palo
    -0.08
    @Autowired
    -0.08
     хват
    -0.08
     Unie
    -0.08
     Plasma
    -0.07
     Serum
    -0.07
    靠谱
    -0.07
     పాల
    -0.07
     итоге
    -0.07
    POSITIVE LOGITS
     whak
    0.08
    agana
    0.08
     agus
    0.08
     प्रवेश
    0.08
    ाझ
    0.08
     نح
    0.07
     Gaeilge
    0.07
     tikanga
    0.07
    נ
    0.07
     الدخول
    0.07
    Activations Density 0.009%

    No Known Activations