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. 67235
    Prev
    Next
    INDEX
    Explanations

    norms or rules

    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
     RMS
    -0.09
     قرب
    -0.08
     potr
    -0.08
     bary
    -0.08
     كبير
    -0.08
     kreat
    -0.07
    apura
    -0.07
     ROI
    -0.07
     GPU
    -0.07
    okeh
    -0.07
    POSITIVE LOGITS
    法规
    0.11
     governing
    0.10
     legislation
    0.10
     statutes
    0.10
     repeal
    0.10
     statutory
    0.09
     aturan
    0.09
    directive
    0.09
     বিধ
    0.09
     घोष
    0.09
    Activations Density 0.026%

    No Known Activations