© 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. 25971
    Prev
    Next
    INDEX
    Explanations

    file paths

    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
     manana
    -0.08
    额度
    -0.08
    ъяс
    -0.08
     déb
    -0.08
     mici
    -0.08
     indeb
    -0.08
    �్
    -0.08
    \Validator
    -0.08
    IVATE
    -0.08
    �
    -0.07
    POSITIVE LOGITS
     当前
    0.10
    -current
    0.08
     বর্ত
    0.08
     THIS
    0.08
    自身
    0.08
     নিজ
    0.07
    _CURRENT
    0.07
    /current
    0.07
     текущ
    0.07
    pathname
    0.07
    Activations Density 0.004%

    No Known Activations