© 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. 129518
    Prev
    Next
    INDEX
    Explanations

    dome

    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
     baseline
    -0.08
     ≥
    -0.08
     �
    -0.08
     côtés
    -0.08
     munch
    -0.07
     brute
    -0.07
     інт
    -0.07
     RO
    -0.07
    ≥
    -0.07
     азы
    -0.07
    POSITIVE LOGITS
     baptism
    0.08
     Pant
    0.08
    مى
    0.08
    복
    0.08
    IFA
    0.08
     casco
    0.08
    دمت
    0.07
    tritt
    0.07
     admire
    0.07
    �ย
    0.07
    Activations Density 0.002%

    No Known Activations