© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21436
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     vollständ
    -0.09
    ात्मक
    -0.08
     completos
    -0.08
     पूर्ण
    -0.08
     સંપૂર્ણ
    -0.08
    ियन
    -0.08
    .complete
    -0.08
    entic
    -0.07
     अनेक
    -0.07
    ाधिक
    -0.07
    POSITIVE LOGITS
    -iṣẹ
    0.10
    uchtet
    0.10
    eftijd
    0.10
    vemente
    0.10
     blower
    0.10
    っぱ
    0.10
    pto
    0.10
    pton
    0.09
    xico
    0.09
     keluar
    0.09
    Activations Density 0.037%

    No Known Activations