© 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. 78290
    Prev
    Next
    INDEX
    Explanations

    alam

    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
     divine
    -0.09
    óvil
    -0.08
     biç
    -0.08
     landed
    -0.08
     ẹrọ
    -0.08
     судь
    -0.08
    -либо
    -0.08
     dwind
    -0.08
     outright
    -0.08
     שאתה
    -0.07
    POSITIVE LOGITS
    699
    0.08
     Responsible
    0.08
     poles
    0.08
     cautiously
    0.07
     Cecilia
    0.07
     waz
    0.07
     Maw
    0.07
     axes
    0.07
    mf
    0.07
     analges
    0.07
    Activations Density 0.002%

    No Known Activations