© 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. 23-RESID-POST-AA
    11. 6649
    Prev
    Next
    INDEX
    Explanations

    六

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (page
    -0.09
    _METADATA
    -0.08
    (metadata
    -0.08
     Vl
    -0.08
    एच
    -0.08
    agana
    -0.08
    andra
    -0.08
    Bass
    -0.08
    anska
    -0.07
    VW
    -0.07
    POSITIVE LOGITS
     паль
    0.09
    root
    0.08
    pakken
    0.08
     afsl
    0.08
     root
    0.08
     détente
    0.07
    親
    0.07
     nélkül
    0.07
     REST
    0.07
    亲
    0.07
    Activations Density 0.001%

    No Known Activations