© 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. 68170
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    िड
    -0.08
    OCs
    -0.08
    ız
    -0.07
    Ctl
    -0.07
     जरूरत
    -0.07
    cnn
    -0.07
    ixin
    -0.07
     interdisciplinary
    -0.07
    oard
    -0.07
     devenir
    -0.07
    POSITIVE LOGITS
     opposite
    0.11
     reversed
    0.10
     symmetrical
    0.10
     symmetric
    0.09
     bipolar
    0.09
     oppos
    0.09
     ವಿರುದ್ಧ
    0.08
    ​ភ
    0.08
     reversing
    0.08
     anton
    0.08
    Activations Density 0.065%

    No Known Activations