© 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. 129488
    Prev
    Next
    INDEX
    Explanations

    the

    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
     spolu
    -0.08
     bởi
    -0.08
    builders
    -0.08
     toes
    -0.07
     kick
    -0.07
     eficiencia
    -0.07
    Bandwidth
    -0.07
     машины
    -0.07
    安心
    -0.07
    maß
    -0.07
    POSITIVE LOGITS
    /**
    0.08
     Abb
    0.07
     pcm
    0.07
     mur
    0.07
     Ä
    0.07
     $$
    0.07
     man
    0.07
     Rit
    0.07
    imleri
    0.07
    /*
    0.06
    Activations Density 0.012%

    No Known Activations