© 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. 103494
    Prev
    Next
    INDEX
    Explanations

    location prepositions

    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
    ၁
    -0.08
    ர்கள்
    -0.08
    āta
    -0.08
     ()
↵
    -0.08
    　在
    -0.08
     Above
    -0.07
    ட்டு
    -0.07
     sobretudo
    -0.07
     postoje
    -0.07
    Above
    -0.07
    POSITIVE LOGITS
     iff
    0.10
     многих
    0.10
     many
    0.10
     every
    0.10
     некоторых
    0.10
     each
    0.10
     большинства
    0.09
     both
    0.09
     several
    0.09
    ，所以
    0.09
    Activations Density 0.047%

    No Known Activations