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. 87841
    Prev
    Next
    INDEX
    Explanations

    geo-engineering

    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
    	cc
    -0.08
     possession
    -0.07
     adapters
    -0.07
     প্রকাশ
    -0.07
     enjoying
    -0.07
    ميز
    -0.07
    :req
    -0.07
     পাওয়া
    -0.07
    (fc
    -0.07
     accolades
    -0.07
    POSITIVE LOGITS
     artificially
    0.15
     planting
    0.14
     artificial
    0.13
     interventions
    0.12
     intervention
    0.12
     künst
    0.12
     Artificial
    0.12
     engineered
    0.11
    人工
    0.11
    Artificial
    0.11
    Activations Density 0.027%

    No Known Activations