© 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. 11-RESID-POST-AA
    11. 75440
    Prev
    Next
    INDEX
    Explanations

    syntax

    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
     Feuerwehr
    -0.08
     Legends
    -0.08
    创业
    -0.08
    	Hash
    -0.08
     lbl
    -0.08
    사업
    -0.07
    Legend
    -0.07
     biaya
    -0.07
     superst
    -0.07
     Hutch
    -0.07
    POSITIVE LOGITS
     grammar
    0.14
     grammatical
    0.13
    结构
    0.12
     estrut
    0.12
     sentence
    0.11
     grammat
    0.11
    _sentence
    0.11
     estrutura
    0.11
     gramm
    0.11
    句
    0.11
    Activations Density 0.015%

    No Known Activations