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. 44172
    Prev
    Next
    INDEX
    Explanations

    shapes and geometry

    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
    (code
    -0.08
     miracles
    -0.08
     نمبر
    -0.08
    (page
    -0.08
    (email
    -0.08
     zorgvuldig
    -0.07
    	self
    -0.07
     नम्बर
    -0.07
    യറ
    -0.07
    (trans
    -0.07
    POSITIVE LOGITS
    combined
    0.11
     combined
    0.10
    Combined
    0.10
     Combined
    0.10
     gemeinsamen
    0.10
     ortaya
    0.10
     combining
    0.09
    workspace
    0.09
     conglomer
    0.09
     объедин
    0.09
    Activations Density 0.026%

    No Known Activations