© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31247
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
     overpriced
    -0.08
    guest
    -0.08
    -0.08
    assist
    -0.08
     alve
    -0.08
     better
    -0.07
    edith
    -0.07
     snapshot
    -0.07
    quest
    -0.07
     obstruct
    -0.07
    POSITIVE LOGITS
     Secretaria
    0.09
     Treasurer
    0.08
     Sociale
    0.08
     Kommentare
    0.08
    -tax
    0.08
    .Application
    0.08
     Positive
    0.08
     eax
    0.08
     lijken
    0.08
     Im
    0.08
    Activations Density 0.000%

    No Known Activations