© 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. 19414
    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
    Profession
    -0.09
    Instit
    -0.08
    ؤ
    -0.08
    Virt
    -0.08
     Academia
    -0.08
     Hochsch
    -0.08
     소비
    -0.08
    Individuals
    -0.08
    Fonte
    -0.08
     universities
    -0.08
    POSITIVE LOGITS
    大厅
    0.15
     hallway
    0.15
     courtyard
    0.14
     cafeteria
    0.14
     cafeter
    0.13
     anthem
    0.11
     auditorium
    0.11
    yard
    0.11
    -yard
    0.11
    -wide
    0.11
    Activations Density 0.016%

    No Known Activations