© 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. 102913
    Prev
    Next
    INDEX
    Explanations

    say "general"

    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
    [new
    -0.09
    .signature
    -0.08
     Signature
    -0.08
     victoire
    -0.08
     الأخير
    -0.08
    signature
    -0.08
    (new
    -0.08
     masterpiece
    -0.08
     artık
    -0.08
    'arrivée
    -0.08
    POSITIVE LOGITS
     algemene
    0.19
    一般
    0.18
     allgeme
    0.18
     പൊത
    0.18
     allgemeinen
    0.17
     सामान्य
    0.17
     générales
    0.17
     algemeen
    0.17
     عامة
    0.17
     gerais
    0.16
    Activations Density 0.020%

    No Known Activations