© 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. 47135
    Prev
    Next
    INDEX
    Explanations

    quickly

    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
    руш
    -0.08
    ldb
    -0.08
     хор
    -0.07
     než
    -0.07
    птом
    -0.07
    ԥ
    -0.07
     ஆக
    -0.07
     phong
    -0.07
    ייז
    -0.07
     பெய
    -0.07
    POSITIVE LOGITS
    赶
    0.09
     teammate
    0.08
     redeem
    0.08
     constructive
    0.08
     frère
    0.07
     tailored
    0.07
     saj
    0.07
    (loc
    0.07
    安排
    0.07
     dressed
    0.07
    Activations Density 0.007%

    No Known Activations