© 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. 91404
    Prev
    Next
    INDEX
    Explanations

    Light polarization and angles

    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
     hormone
    -0.08
     endocrine
    -0.08
    Dungeon
    -0.08
    _THREAD
    -0.08
    _datetime
    -0.08
     tässä
    -0.08
     Testosterone
    -0.08
     debía
    -0.08
    bishop
    -0.08
    ুদ
    -0.08
    POSITIVE LOGITS
     Brew
    0.08
     स्वी
    0.07
     Flug
    0.07
     harsh
    0.07
     optimale
    0.07
     Fälle
    0.07
    NEG
    0.07
    Forbidden
    0.07
     Kontakt
    0.07
     proib
    0.07
    Activations Density 0.003%

    No Known Activations