© 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. 23-RESID-POST-AA
    11. 51052
    Prev
    Next
    INDEX
    Explanations

    Post-operative/technical procedures

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underlying
    -0.12
     underneath
    -0.11
     предвар
    -0.11
     upfront
    -0.11
     beforehand
    -0.11
     outskirts
    -0.11
     préalable
    -0.11
     upstream
    -0.10
     מראש
    -0.10
    Underlying
    -0.10
    POSITIVE LOGITS
     activities
    0.12
    tlement
    0.12
     गतिविध
    0.10
     Aktivitäten
    0.10
     activiteiten
    0.10
    /on
    0.10
     Activities
    0.10
     adjustments
    0.10
     aktiviteter
    0.10
     effects
    0.09
    Activations Density 0.061%

    No Known Activations