© 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. 23-RESID-POST-AA
    11. 48056
    Prev
    Next
    INDEX
    Explanations

    such

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     यस्तो
    -0.10
     dergelijke
    -0.10
     אָדער
    -0.10
    �ს
    -0.10
     宝盈
    -0.10
     આવા
    -0.10
    �ენ
    -0.10
     圣亚
    -0.09
     同创
    -0.09
    Such
    -0.09
    POSITIVE LOGITS
     that
    0.13
     as
    0.11
     कि
    0.10
     an
    0.10
     a
    0.10
    That
    0.10
     kwamba
    0.09
     rằng
    0.09
     dass
    0.09
     کہ
    0.09
    Activations Density 0.063%

    No Known Activations