© 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. 3-RESID-POST-AA
    11. 12881
    Prev
    Next
    INDEX
    Explanations

    frem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kin
    -0.08
     musk
    -0.07
    ميت
    -0.07
    МИ
    -0.07
     MODE
    -0.07
     mi
    -0.07
     estad
    -0.07
    CCA
    -0.07
     sava
    -0.07
    ես
    -0.07
    POSITIVE LOGITS
    EAN
    0.08
    Sorry
    0.07
    왜
    0.07
    خواه
    0.07
    igis
    0.07
    lıkl
    0.07
     احت
    0.07
    SF
    0.07
    र्ख
    0.07
    ोत
    0.07
    Activations Density 0.001%

    No Known Activations