© 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. 68057
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     وعدم
    -0.08
     indir
    -0.08
    _inds
    -0.08
     conceivable
    -0.08
     систему
    -0.08
     desperate
    -0.08
     ಅವಕಾಶ
    -0.08
    Indirect
    -0.08
     resemblance
    -0.07
     sift
    -0.07
    POSITIVE LOGITS
     keynote
    0.13
     discussing
    0.11
     speakers
    0.10
     experts
    0.10
     expertise
    0.09
     эксперт
    0.09
     perspectives
    0.09
     invité
    0.09
    专家
    0.09
     বক্ত
    0.09
    Activations Density 0.205%

    No Known Activations