© 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. 102408
    Prev
    Next
    INDEX
    Explanations

    Prepositions of location

    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
     jährlich
    -0.08
     이번
    -0.08
    isieren
    -0.08
     올해
    -0.08
     investig
    -0.08
    ():↵↵
    -0.08
     Investigación
    -0.07
     ();↵//
    -0.07
     Tamanna
    -0.07
     pesquisa
    -0.07
    POSITIVE LOGITS
     amidst
    0.19
     beneath
    0.18
     surrounded
    0.18
     nestled
    0.17
     perched
    0.17
     atop
    0.17
    ใต้
    0.17
     amid
    0.17
     outdoors
    0.17
     under
    0.16
    Activations Density 0.082%

    No Known Activations