© 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. 26528
    Prev
    Next
    INDEX
    Explanations

    yachts and/or jets

    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
     scarves
    -0.08
     Zig
    -0.08
    怪
    -0.07
     preservatives
    -0.07
    作用
    -0.07
    易
    -0.07
    iction
    -0.07
    ført
    -0.07
    �
    -0.07
    Simpl
    -0.07
    POSITIVE LOGITS
    ISI
    0.08
     рос
    0.08
     interoper
    0.08
     qualsiasi
    0.08
     comunica
    0.08
     Bach
    0.07
     searched
    0.07
     comun
    0.07
    ikos
    0.07
     Comun
    0.07
    Activations Density 0.006%

    No Known Activations