© 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. 97240
    Prev
    Next
    INDEX
    Explanations

    Dota 2 particle files

    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
    _rm
    -0.08
     máxim
    -0.07
    Dist
    -0.07
     ア
    -0.07
    Picking
    -0.07
    _overlap
    -0.07
     Numbers
    -0.07
    'all
    -0.07
    Fix
    -0.07
     Fix
    -0.07
    POSITIVE LOGITS
     esti
    0.09
    Ifc
    0.08
    stva
    0.08
     χρη
    0.08
     Khasi
    0.08
     utu
    0.08
     suur
    0.08
    口诀
    0.08
     devait
    0.08
     khas
    0.08
    Activations Density 0.000%

    No Known Activations