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. 102855
    Prev
    Next
    INDEX
    Explanations

    elephants

    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
     Guaranteed
    -0.08
     aerobic
    -0.08
     rápida
    -0.08
     tert
    -0.08
     unemployment
    -0.08
     guaranteed
    -0.08
     гарант
    -0.08
     anaer
    -0.07
     rápido
    -0.07
    _manager
    -0.07
    POSITIVE LOGITS
     elephants
    0.13
     majestic
    0.10
     elephant
    0.10
     afric
    0.10
     majest
    0.09
     Elephant
    0.09
     trekk
    0.08
    Bots
    0.08
     awe
    0.08
    phants
    0.08
    Activations Density 0.008%

    No Known Activations