© 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. 253
    Prev
    Next
    INDEX
    Explanations

    Uncertainty

    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
     Fif
    -0.08
     بودن
    -0.08
     Kol
    -0.08
     Petsc
    -0.08
     interessa
    -0.07
    十二
    -0.07
     Fug
    -0.07
     mee
    -0.07
     demais
    -0.07
     manche
    -0.07
    POSITIVE LOGITS
     eleg
    0.08
     Belgium
    0.08
    itr
    0.08
    of
    0.08
    'eff
    0.07
    ‌ನ
    0.07
     используя
    0.07
    via
    0.07
    slots
    0.07
    Inspired
    0.07
    Activations Density 0.054%

    No Known Activations