© 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. 47761
    Prev
    Next
    INDEX
    Explanations

    binary

    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
    วิ
    -0.08
     Brew
    -0.07
     thigh
    -0.07
    endig
    -0.07
     drastic
    -0.07
     massive
    -0.07
    ρά
    -0.07
    विश
    -0.07
    started
    -0.07
    avail
    -0.07
    POSITIVE LOGITS
    Multiplicity
    0.09
    拆
    0.09
     unresolved
    0.08
     venture
    0.08
     سلم
    0.08
    -field
    0.08
    -member
    0.08
     Fotograf
    0.08
     splitting
    0.08
     integrante
    0.08
    Activations Density 0.003%

    No Known Activations