© 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. 19618
    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
     registrations
    -0.07
    Overrides
    -0.07
    Compare
    -0.07
    计算
    -0.07
     souhaiter
    -0.07
    Guardian
    -0.07
    (ph
    -0.07
     cicl
    -0.07
    Authorities
    -0.07
    Preference
    -0.07
    POSITIVE LOGITS
    ÷
    0.11
     тоже
    0.10
     divisible
    0.10
     ebenfalls
    0.10
     división
    0.10
    irió
    0.09
    扒开
    0.09
     likewise
    0.09
    ोंने
    0.09
     �
    0.09
    Activations Density 0.007%

    No Known Activations