Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111948
    Prev
    Next
    INDEX
    Explanations

    Blend

    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
    Comparison
    -0.08
    Located
    -0.08
    >(*
    -0.07
    wydd
    -0.07
    gomery
    -0.07
     recre
    -0.07
    >()
    -0.07
    rops
    -0.07
    iets
    -0.07
    .SET
    -0.07
    POSITIVE LOGITS
    !↵↵
    0.13
    !↵
    0.11
    !"
    0.10
     story
    0.10
    !↵↵
    0.10
    !).↵↵
    0.10
    故事
    0.10
    !
    ↵
    0.09
     Stories
    0.09
    !");↵
    0.09
    Activations Density 1.531%

    No Known Activations