© 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. 95049
    Prev
    Next
    INDEX
    Explanations

    Language diacritic questions

    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
    _PROM
    -0.08
    Disposed
    -0.08
     Christchurch
    -0.08
     Femin
    -0.07
    �
    -0.07
    disposed
    -0.07
    önt
    -0.07
     opgericht
    -0.07
     woody
    -0.07
     inertia
    -0.07
    POSITIVE LOGITS
     النظر
    0.09
     szt
    0.08
     extending
    0.08
    논
    0.08
     سبح
    0.08
    loops
    0.07
    238
    0.07
    NO
    0.07
    نظر
    0.07
     نظر
    0.07
    Activations Density 0.000%

    No Known Activations