© 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. 11-RESID-POST-AA
    11. 31459
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
    Saga
    -0.09
    _major
    -0.08
     사업
    -0.08
    lease
    -0.08
     FAQ
    -0.08
    letse
    -0.08
    ustele
    -0.08
     тарап
    -0.08
    _collect
    -0.08
    .Gray
    -0.08
    POSITIVE LOGITS
     anchored
    0.11
     anch
    0.10
     anchor
    0.10
     anchors
    0.10
    Anch
    0.10
     newline
    0.09
     Anch
    0.09
    anchors
    0.09
     punctuation
    0.09
     terminar
    0.09
    Activations Density 0.003%

    No Known Activations