© 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. 102161
    Prev
    Next
    INDEX
    Explanations

    Onomatopoeia

    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
     initial
    -0.09
     special
    -0.08
     x
    -0.08
     be
    -0.07
     être
    -0.07
     occur
    -0.07
     typed
    -0.07
     (()
    -0.07
     partial
    -0.07
     tengo
    -0.07
    POSITIVE LOGITS
    odwi
    0.10
    undai
    0.10
    okset
    0.10
    랍니다
    0.10
    aneamente
    0.10
    issaa
    0.10
    ahuan
    0.10
    atalaga
    0.09
    amisel
    0.09
    ahoo
    0.09
    Activations Density 0.003%

    No Known Activations