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. 8514
    Prev
    Next
    INDEX
    Explanations

    :

    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
    /look
    -0.08
    iners
    -0.08
    Adm
    -0.07
    ultat
    -0.07
    Fld
    -0.07
     Kana
    -0.07
    /internal
    -0.07
    �果
    -0.07
    /");↵
    -0.07
    Kana
    -0.07
    POSITIVE LOGITS
    -mal
    0.08
     hội
    0.08
    ωση
    0.08
    clinical
    0.08
     welcoming
    0.08
     degrading
    0.08
    -themed
    0.08
    ∀
    0.07
     Beim
    0.07
     με
    0.07
    Activations Density 0.000%

    No Known Activations