© 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. 102927
    Prev
    Next
    INDEX
    Explanations

    \

    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
     or
    -0.08
     πολ
    -0.08
    :↵↵
    -0.08
     m
    -0.08
     বা
    -0.08
     Height
    -0.07
     →↵
    -0.07
     retrieving
    -0.07
    ঃ
    -0.07
     mètres
    -0.07
    POSITIVE LOGITS
    sum
    0.11
    جموع
    0.11
    串一
    0.11
    天天送
    0.10
    平台招商
    0.10
    平台开户
    0.10
    уҷ
    0.10
    人人看
    0.10
    ӯш
    0.10
    综合网
    0.10
    Activations Density 0.008%

    No Known Activations