© 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. 2647
    Prev
    Next
    INDEX
    Explanations

    id

    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
    Sou
    -0.08
     Bras
    -0.08
     ngo
    -0.08
     Idol
    -0.08
    ����
    -0.07
    Sous
    -0.07
     Yose
    -0.07
    Gtk
    -0.07
    Lect
    -0.07
     Yo
    -0.07
    POSITIVE LOGITS
    äki
    0.08
    ೂಲ
    0.08
    ้อน
    0.08
    AML
    0.08
    bereiche
    0.08
    gevoel
    0.08
    ünft
    0.07
     ruling
    0.07
    mee
    0.07
    sec
    0.07
    Activations Density 0.000%

    No Known Activations