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. 90276
    Prev
    Next
    INDEX
    Explanations

    Funding and fiscal policy

    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
    ..\
    -0.08
    Mime
    -0.08
     వరకు
    -0.08
     Before
    -0.08
     Anyone
    -0.08
    .Media
    -0.08
    र्श
    -0.07
     ניסיון
    -0.07
    -one
    -0.07
    /video
    -0.07
    POSITIVE LOGITS
     subsidies
    0.11
     subsidy
    0.11
     equitable
    0.10
     federal
    0.10
    imbursement
    0.09
     reimbursement
    0.09
     revenues
    0.09
     territ
    0.09
    比例
    0.09
    待遇
    0.09
    Activations Density 0.026%

    No Known Activations