© 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. 75749
    Prev
    Next
    INDEX
    Explanations

    hippocampus

    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
     escalation
    -0.09
     vlas
    -0.09
     Schwe
    -0.08
     escal
    -0.08
     শ্রম
    -0.08
    ÉS
    -0.08
     Peach
    -0.08
     ESG
    -0.07
     zapr
    -0.07
     unes
    -0.07
    POSITIVE LOGITS
     hippoc
    0.12
     ori
    0.09
     recuerdo
    0.08
    .Mongo
    0.08
     Mongo
    0.08
    emory
    0.08
     Epis
    0.07
     öğren
    0.07
     impaired
    0.07
     Zelda
    0.07
    Activations Density 0.004%

    No Known Activations