© 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. 78317
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     vias
    -0.09
    umele
    -0.08
    Scr
    -0.08
    ods
    -0.08
    Soll
    -0.07
    ตลาด
    -0.07
     segn
    -0.07
    rosso
    -0.07
    ATL
    -0.07
    arbeitung
    -0.07
    POSITIVE LOGITS
    ，因此
    0.10
    ，所以
    0.10
     હોવાથી
    0.09
     있기
    0.09
     থেকে
    0.08
    தால்
    0.08
     dahilan
    0.08
     আদ
    0.08
     কারণে
    0.08
    平均
    0.08
    Activations Density 0.052%

    No Known Activations