© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 1007
    Prev
    Next
    INDEX
    Explanations

    Dialogue snippets and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abs
    -0.08
    581
    -0.08
     isolation
    -0.08
     aisl
    -0.08
     aislamiento
    -0.08
    185
    -0.07
     reasonably
    -0.07
     ↵  ↵↵
    -0.07
     isolate
    -0.07
     behave
    -0.07
    POSITIVE LOGITS
    .icons
    0.08
     보여
    0.08
    .jdesktop
    0.08
     Koe
    0.08
    কে
    0.08
    .Right
    0.07
    .place
    0.07
    へ
    0.07
    (Icons
    0.07
    Dollar
    0.07
    Activations Density 0.057%

    No Known Activations