© 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. 102188
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    。据
    -0.11
    ..."
    -0.10
    。然而
    -0.09
    ..."↵↵
    -0.09
     lately
    -0.09
    —
    -0.09
     thirteen
    -0.09
     désormais
    -0.09
     pourtant
    -0.08
    ，却
    -0.08
    POSITIVE LOGITS
     ggf
    0.15
    /background
    0.11
    /use
    0.10
    /example
    0.10
     eventueel
    0.10
     hoặc
    0.09
    /result
    0.09
    /oder
    0.09
    /examples
    0.09
     SMART
    0.09
    Activations Density 0.119%

    No Known Activations