© 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. 7-RESID-POST-AA
    11. 1159
    Prev
    Next
    INDEX
    Explanations

    poetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     આવ
    -0.08
    _comb
    -0.08
     Reinh
    -0.08
    anko
    -0.08
    ਿਰ
    -0.07
    Anthony
    -0.07
     neem
    -0.07
    ritic
    -0.07
     Gurb
    -0.07
     Kalk
    -0.07
    POSITIVE LOGITS
     suck
    0.08
     गीत
    0.08
    .closed
    0.08
    astes
    0.08
     gov
    0.08
    一级
    0.08
     thanh
    0.07
    .elements
    0.07
    scss
    0.07
     gi
    0.07
    Activations Density 0.003%

    No Known Activations