© 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. 11-RESID-POST-AA
    11. 47535
    Prev
    Next
    INDEX
    Explanations

    desired

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    province
    -0.08
    алаш
    -0.07
     menjaga
    -0.07
    .Win
    -0.07
    альном
    -0.07
    (rot
    -0.07
     rok
    -0.07
    WIN
    -0.07
    eniu
    -0.07
     WARRANTIES
    -0.07
    POSITIVE LOGITS
     auparavant
    0.11
     давно
    0.10
    终于
    0.10
    以来
    0.09
     endlich
    0.09
     elusive
    0.09
     eindelijk
    0.08
    itters
    0.08
     never
    0.08
    43
    0.08
    Activations Density 0.094%

    No Known Activations