© 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. 25104
    Prev
    Next
    INDEX
    Explanations

    frozen treats

    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
     competência
    -0.08
     infertility
    -0.08
     immobili
    -0.08
    Benchmark
    -0.08
    Occurred
    -0.08
    -informed
    -0.08
     betr
    -0.08
     pouvoir
    -0.08
     impeccable
    -0.07
     elastic
    -0.07
    POSITIVE LOGITS
    Stick
    0.08
    ité
    0.08
     accessories
    0.08
     Color
    0.08
    �
    0.08
     cabin
    0.08
     Handbook
    0.07
     cabins
    0.07
    มือ
    0.07
    eurs
    0.07
    Activations Density 0.003%

    No Known Activations