© 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. 97556
    Prev
    Next
    INDEX
    Explanations

    cleaning products

    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
     takım
    -0.08
    oral
    -0.08
    orale
    -0.08
    usu
    -0.08
    olid
    -0.08
     inder
    -0.07
    oria
    -0.07
     pretty
    -0.07
    irde
    -0.07
     એને
    -0.07
    POSITIVE LOGITS
    িল
    0.08
    cast
    0.08
     கால
    0.08
    LS
    0.07
    ilhas
    0.07
    _construct
    0.07
    Па
    0.07
    -Pr
    0.07
    ilha
    0.07
    ন্ত
    0.07
    Activations Density 0.001%

    No Known Activations