© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44800
    Prev
    Next
    INDEX
    Explanations

    invisible, hidden

    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
    很
    -0.08
    奋斗
    -0.08
     casc
    -0.07
     rustig
    -0.07
    ertjes
    -0.07
     marts
    -0.07
     Praise
    -0.07
     temples
    -0.07
    .Abs
    -0.07
    huizen
    -0.07
    POSITIVE LOGITS
    Blind
    0.10
    .decrypt
    0.10
     секрет
    0.10
    .encrypt
    0.10
    blind
    0.10
    Hidden
    0.10
     ultraviolet
    0.09
    .secret
    0.09
    hidden
    0.09
    Decrypt
    0.09
    Activations Density 0.030%

    No Known Activations