© 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. 77997
    Prev
    Next
    INDEX
    Explanations

    "exactly one" logic problems

    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
    紙
    -0.08
     alternate
    -0.08
    don
    -0.07
     pay
    -0.07
    elsey
    -0.07
     же
    -0.07
    set
    -0.07
     medic
    -0.07
     California
    -0.06
     начала
    -0.06
    POSITIVE LOGITS
     überhaupt
    0.10
     comprehensive
    0.09
     tällä
    0.09
    prehensive
    0.09
     encima
    0.09
    <Long
    0.08
     sèl
    0.08
     sequer
    0.08
     plethora
    0.08
     einzige
    0.08
    Activations Density 0.055%

    No Known Activations