© 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. 11-RESID-POST-AA
    11. 114255
    Prev
    Next
    INDEX
    Explanations

    defining populations

    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
    onk
    -0.09
    Signs
    -0.08
     signs
    -0.08
    Spacing
    -0.08
    =format
    -0.08
     occured
    -0.08
    (template
    -0.07
    .ERROR
    -0.07
     templates
    -0.07
    (prev
    -0.07
    POSITIVE LOGITS
     collecte
    0.12
     collecting
    0.11
     সংগ্র
    0.11
    集合
    0.11
    全集
    0.11
     Collect
    0.11
     collects
    0.11
     collected
    0.11
     collectie
    0.10
     Collection
    0.10
    Activations Density 0.011%

    No Known Activations