© 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. 51051
    Prev
    Next
    INDEX
    Explanations

    summary checklist away

    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
     seminal
    -0.08
    *A
    -0.07
    *i
    -0.07
     онда
    -0.07
    Precis
    -0.07
    Characteristics
    -0.07
     должны
    -0.07
    Details
    -0.07
     Logical
    -0.07
    -0.07
    POSITIVE LOGITS
     you
    0.14
     You
    0.12
    你
    0.12
     você
    0.12
     you're
    0.12
     you'd
    0.11
     😊
    0.11
     ayudarte
    0.11
     :)↵↵
    0.11
     checklist
    0.11
    Activations Density 0.053%
    No Known Activations