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. 9049
    Prev
    Next
    INDEX
    Explanations

    authenticator

    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
     zj
    -0.08
     cwd
    -0.07
    -0.07
    ząd
    -0.07
     Wij
    -0.07
    water
    -0.07
    =cut
    -0.07
    Water
    -0.07
     Ct
    -0.07
    MAS
    -0.07
    POSITIVE LOGITS
     eingerichtet
    0.09
     sincron
    0.09
     भुग
    0.09
    寶
    0.08
    셀
    0.08
     baker
    0.08
    ’oubl
    0.08
     cript
    0.08
     Riley
    0.08
     encoded
    0.08
    Activations Density 0.001%

    No Known Activations