© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96862
    Prev
    Next
    INDEX
    Explanations

    media recognition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rebellion
    -0.09
     overthrow
    -0.08
     trabalhador
    -0.08
     revolt
    -0.07
     uphe
    -0.07
     tyranny
    -0.07
     täiel
    -0.07
     xor
    -0.07
     capitalism
    -0.07
     отход
    -0.07
    POSITIVE LOGITS
    Featured
    0.18
     recognition
    0.17
     featured
    0.17
     Featured
    0.17
    掲載
    0.16
     placements
    0.16
     accolades
    0.16
     Recognition
    0.16
    Recognition
    0.16
    featured
    0.15
    Activations Density 0.093%

    No Known Activations