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. 119174
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ASTM
    -0.10
     textile
    -0.09
     Coch
    -0.08
     stimulation
    -0.08
     Schl
    -0.08
     Ethernet
    -0.08
     Wohn
    -0.08
     stimuler
    -0.07
     Lease
    -0.07
     polyester
    -0.07
    POSITIVE LOGITS
     teammate
    0.10
    -player
    0.09
    英雄
    0.09
     убий
    0.08
     tactical
    0.08
     launcher
    0.08
     scripted
    0.08
     MMORPG
    0.08
     campeão
    0.08
    Team
    0.08
    Activations Density 0.016%

    No Known Activations