© 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. 19-RESID-POST-AA
    11. 102892
    Prev
    Next
    INDEX
    Explanations

    degrees

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Skill
    -0.08
     vans
    -0.07
     dwóch
    -0.07
     njih
    -0.07
     deform
    -0.07
     seriam
    -0.07
     diferença
    -0.07
    Dispose
    -0.07
     arenas
    -0.07
    Such
    -0.07
    POSITIVE LOGITS
    °
    0.13
    %'
    0.11
    ^\
    0.10
    этг
    0.10
    _minutes
    0.10
     °
    0.10
    եմ
    0.10
     byw
    0.09
    °↵↵
    0.09
    °C
    0.09
    Activations Density 0.009%

    No Known Activations