© 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. 19-RESID-POST-AA
    11. 102583
    Prev
    Next
    INDEX
    Explanations

    cone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WINDOWS
    -0.12
     transactional
    -0.11
     Windows
    -0.11
    Windows
    -0.11
     गिरफ्त
    -0.11
    transactions
    -0.11
     HWND
    -0.11
     Transaction
    -0.10
     transact
    -0.10
     Barclays
    -0.10
    POSITIVE LOGITS
     cone
    0.24
     مخروط
    0.22
     cones
    0.20
    cone
    0.20
     cylindrical
    0.19
     cylinder
    0.19
     Cone
    0.19
    Cone
    0.18
     cono
    0.18
     цилинд
    0.18
    Activations Density 0.033%

    No Known Activations