© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69886
    Prev
    Next
    INDEX
    Explanations

    programming rules and types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOC
    -0.08
     COB
    -0.08
    整理
    -0.08
    Maur
    -0.07
     beneficiaries
    -0.07
    Maintenance
    -0.07
    망
    -0.07
     amplified
    -0.07
    -0.07
     me
    -0.07
    POSITIVE LOGITS
     custom
    0.13
    _Custom
    0.12
     personnalisé
    0.12
     Custom
    0.12
    	custom
    0.12
    custom
    0.11
     personalizado
    0.11
    .Custom
    0.11
    .custom
    0.11
     bespoke
    0.11
    Activations Density 0.010%
    No Known Activations