© 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. 75806
    Prev
    Next
    INDEX
    Explanations

    等

    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
     Joke
    -0.08
    alini
    -0.08
     intervenir
    -0.07
    Teste
    -0.07
    CELL
    -0.07
    liwe
    -0.07
     Typical
    -0.07
     Anyway
    -0.07
     tweeted
    -0.07
     Okay
    -0.07
    POSITIVE LOGITS
     nhau
    0.12
    ां
    0.10
    .Equal
    0.09
    .equal
    0.09
    _equal
    0.09
     बराब
    0.09
    ार्थ
    0.09
    กับ
    0.09
    .eq
    0.08
     igualdade
    0.08
    Activations Density 0.035%

    No Known Activations