© 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. 96216
    Prev
    Next
    INDEX
    Explanations

    ight

    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
    ATION
    -0.08
    shini
    -0.08
     המכ
    -0.08
    ATIONS
    -0.08
    ibição
    -0.08
     hoʻon
    -0.08
    andidato
    -0.08
     ùn
    -0.08
    ční
    -0.07
     influx
    -0.07
    POSITIVE LOGITS
    arrow
    0.17
     arrow
    0.12
    _arrow
    0.12
    ar
    0.11
     arrows
    0.10
    -arrow
    0.10
    .arrow
    0.10
    .Typed
    0.10
    箭
    0.10
    Arrow
    0.09
    Activations Density 0.000%

    No Known Activations