© 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. 49239
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    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
    quettes
    -0.09
     молод
    -0.08
     Перв
    -0.08
     young
    -0.08
     youngsters
    -0.08
     جهانی
    -0.08
    ailleurs
    -0.08
     younger
    -0.08
     diariamente
    -0.08
     молодых
    -0.08
    POSITIVE LOGITS
    ngel
    0.11
    ngulo
    0.11
    ngeles
    0.10
    ure
    0.10
    NG
    0.09
    nade
    0.09
    No
    0.08
    use
    0.08
    gave
    0.08
    or
    0.08
    Activations Density 0.000%

    No Known Activations