© 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. 22305
    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
    irge
    -0.08
     निर्णय
    -0.07
     在
    -0.07
     Density
    -0.07
     தொடர்ந்து
    -0.07
     સતત
    -0.07
     كث
    -0.07
     加
    -0.07
     Management
    -0.07
    .Gravity
    -0.07
    POSITIVE LOGITS
     innocence
    0.17
     innocent
    0.15
     innoc
    0.13
     civilians
    0.11
    洁
    0.11
     Innoc
    0.10
     childish
    0.10
     ಮಕ್ಕಳ
    0.10
    -looking
    0.10
    ieuze
    0.10
    Activations Density 0.008%

    No Known Activations