© 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. 30215
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    లా
    -0.08
     DU
    -0.08
    ziemy
    -0.07
     것은
    -0.07
    ide
    -0.07
    �
    -0.07
     것입니다
    -0.07
    נן
    -0.07
     LAD
    -0.07
    ặp
    -0.07
    POSITIVE LOGITS
     আ
    0.08
     kir
    0.07
     vih
    0.07
     bsp
    0.07
     nachhaltig
    0.07
     kil
    0.07
     жал
    0.07
     cek
    0.07
     ogl
    0.07
     citron
    0.07
    Activations Density 0.071%

    No Known Activations