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. 23-RESID-POST-AA
    6. 98598
    Prev
    Next
    INDEX
    Explanations

    Staging, sandbox environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Helvetica
    -0.08
     الكبيرة
    -0.08
    орм
    -0.08
     motor
    -0.08
    برى
    -0.08
    ;complex
    -0.08
     comprimento
    -0.07
     scalar
    -0.07
     societal
    -0.07
    iomanip
    -0.07
    POSITIVE LOGITS
     staging
    0.26
     sandbox
    0.23
    sandbox
    0.22
    Sandbox
    0.22
     Sandbox
    0.21
    沙
    0.19
     dev
    0.18
     DEV
    0.18
     environments
    0.17
    andbox
    0.17
    Activations Density 0.036%

    No Known Activations