© 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. 19-RESID-POST-AA
    11. 102981
    Prev
    Next
    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _HORIZONTAL
    -0.09
    /styles
    -0.09
     shaded
    -0.09
     cellpadding
    -0.09
     horiz
    -0.09
     codigo
    -0.08
    /&
    -0.08
     shading
    -0.08
     vroeger
    -0.08
    ವಿಡ್
    -0.08
    POSITIVE LOGITS
    section
    0.09
    .publisher
    0.07
     allergic
    0.07
     однако
    0.07
     аллерг
    0.07
     section
    0.07
     população
    0.07
     المشروع
    0.07
     attività
    0.07
     influenza
    0.07
    Activations Density 0.001%

    No Known Activations