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. 113831
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems

    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
    ాప్తంగా
    -0.07
    370
    -0.07
    ווא
    -0.07
    _OVER
    -0.07
     Emily
    -0.07
     Magdal
    -0.07
    _ADD
    -0.07
     accordance
    -0.07
    daemon
    -0.07
    _over
    -0.07
    POSITIVE LOGITS
    ledning
    0.09
    ABCDE
    0.08
     SCO
    0.08
     desse
    0.08
     détail
    0.08
    ках
    0.08
     //<
    0.07
     жд
    0.07
     ince
    0.07
    。所以
    0.07
    Activations Density 0.454%

    No Known Activations