© 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. 129399
    Prev
    Next
    INDEX
    Explanations

    because

    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
    jera
    -0.07
     lieber
    -0.07
     whale
    -0.07
    Caps
    -0.07
     periód
    -0.07
     recommending
    -0.07
    research
    -0.07
     juven
    -0.07
    جي
    -0.07
    _STRING
    -0.07
    POSITIVE LOGITS
     Çünkü
    0.13
     çünkü
    0.12
    因为
    0.11
     потому
    0.11
     കാരണം
    0.10
     evidenced
    0.10
     કારણ
    0.10
     Afinal
    0.10
     because
    0.10
     doordat
    0.10
    Activations Density 0.066%

    No Known Activations