© 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. 78902
    Prev
    Next
    INDEX
    Explanations

    consumer wants and expectations

    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
    irut
    -0.08
     schöne
    -0.08
     جيدة
    -0.08
     сколько
    -0.08
     útiles
    -0.08
     çalışma
    -0.07
     laufen
    -0.07
     выполнить
    -0.07
     quaternion
    -0.07
     الإصابة
    -0.07
    POSITIVE LOGITS
     preferences
    0.11
     prefers
    0.11
     insists
    0.10
     prefer
    0.10
     prefere
    0.10
    .preferences
    0.09
     предъяв
    0.09
     preference
    0.09
    _preferences
    0.09
     satın
    0.09
    Activations Density 0.090%

    No Known Activations