© 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. 24611
    Prev
    Next
    INDEX
    Explanations

    ist

    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
     gyms
    -0.08
     системой
    -0.08
     Cre
    -0.07
    >"+
    -0.07
    ાર્ટ
    -0.07
    ="+
    -0.07
     crease
    -0.07
    ार्ट
    -0.07
    "+
    -0.07
     aplikasi
    -0.07
    POSITIVE LOGITS
    dol
    0.09
    улу
    0.07
    inol
    0.07
    avel
    0.07
     enzym
    0.07
     fingertips
    0.07
    ility
    0.07
     transitions
    0.07
     relate
    0.07
     relating
    0.07
    Activations Density 0.001%

    No Known Activations