© 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. 7-RESID-POST-AA
    11. 1401
    Prev
    Next
    INDEX
    Explanations

    拼

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Primera
    -0.08
     Jap
    -0.08
     SQ
    -0.08
     wrath
    -0.08
     tetr
    -0.08
     cin
    -0.08
     Gou
    -0.08
     Kek
    -0.08
    ব্য
    -0.08
     �
    -0.08
    POSITIVE LOGITS
     aff
    0.09
    أ
    0.09
     mas
    0.08
    574
    0.07
     concours
    0.07
    �়ে
    0.07
     evaluating
    0.07
    搏
    0.07
     �
    0.07
     evaluate
    0.07
    Activations Density 0.001%

    No Known Activations