© 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. 47925
    Prev
    Next
    INDEX
    Explanations

    differ

    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
     swojej
    -0.08
     Tru
    -0.07
    LTE
    -0.07
    Cet
    -0.07
    LC
    -0.07
     kerja
    -0.07
     влад
    -0.07
    _tar
    -0.07
     LC
    -0.07
    burn
    -0.07
    POSITIVE LOGITS
    ச
    0.09
    距
    0.08
    有关
    0.08
    اف
    0.08
    -अलग
    0.08
    �
    0.08
     antip
    0.07
     infinit
    0.07
     х
    0.07
     há
    0.07
    Activations Density 0.013%

    No Known Activations