© 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. 103290
    Prev
    Next
    INDEX
    Explanations

    anything

    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
     direttamente
    -0.09
     directement
    -0.08
     इतना
    -0.08
     सीधे
    -0.08
     simples
    -0.08
     straightforward
    -0.08
     unmittel
    -0.08
     sederhana
    -0.08
     सरल
    -0.08
     simpler
    -0.08
    POSITIVE LOGITS
    anything
    0.15
    (any
    0.14
     Undefined
    0.14
     qualsiasi
    0.14
    -any
    0.13
     아무
    0.13
    undefined
    0.13
     Any
    0.13
     undefined
    0.13
     எந்த
    0.13
    Activations Density 0.023%

    No Known Activations