© 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. 607
    Prev
    Next
    INDEX
    Explanations

    Project development

    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
     Cipher
    -0.09
     overpriced
    -0.09
     poisonous
    -0.09
     dangerous
    -0.08
     celestial
    -0.08
     disgr
    -0.08
     cipher
    -0.08
     drunken
    -0.08
     decrypted
    -0.08
     Dangerous
    -0.08
    POSITIVE LOGITS
     initiatives
    0.13
     iniciativas
    0.12
     UNICEF
    0.12
    开展
    0.12
    Drupal
    0.11
     Outreach
    0.11
     outreach
    0.11
     underway
    0.11
    党建
    0.11
     NGOs
    0.11
    Activations Density 0.237%

    No Known Activations