Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77187
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
     FE
    -0.08
     ANY
    -0.08
     sign
    -0.08
     domin
    -0.07
     basically
    -0.07
     elevate
    -0.07
     elevation
    -0.07
     erwäh
    -0.07
    _BG
    -0.07
     rév
    -0.07
    POSITIVE LOGITS
     krijg
    0.08
    টি
    0.08
    ই
    0.08
    ું
    0.07
     Verte
    0.07
     Максим
    0.07
     আই
    0.07
     Dairy
    0.07
     Yan
    0.07
     sead
    0.07
    Activations Density 0.351%

    No Known Activations