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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30554
    Prev
    Next
    INDEX
    Explanations

    find

    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
     revolving
    -0.08
     contempl
    -0.08
     contem
    -0.08
     MICRO
    -0.08
     stattfinden
    -0.07
     sixteen
    -0.07
    ہر
    -0.07
     pregnancy
    -0.07
     reminders
    -0.07
     SPE
    -0.07
    POSITIVE LOGITS
     Ded
    0.08
     indirectly
    0.08
     kule
    0.08
     coef
    0.08
     ded
    0.08
     tecido
    0.08
     коэффици
    0.08
     deduction
    0.08
     θ
    0.08
    cert
    0.07
    Activations Density 0.045%

    No Known Activations