© 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. 78345
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
    绿
    -0.08
     إف
    -0.08
     CORPOR
    -0.07
     Mesin
    -0.07
    '}>↵
    -0.07
     CASH
    -0.07
     SAG
    -0.07
     dahilan
    -0.07
     green
    -0.07
    -green
    -0.07
    POSITIVE LOGITS
     aproxim
    0.08
     hợp
    0.07
    ंप
    0.07
    ेंस
    0.07
     đảm
    0.07
    ędzie
    0.07
    �
    0.07
    credit
    0.07
     biệt
    0.07
    ಾಟ
    0.07
    Activations Density 0.010%

    No Known Activations