© 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. 6153
    Prev
    Next
    INDEX
    Explanations

    actions

    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
     citing
    -0.11
    答案
    -0.10
    -solving
    -0.10
     answering
    -0.10
    怎么看
    -0.10
     prides
    -0.10
     proofreading
    -0.10
     Hern
    -0.09
     cites
    -0.09
     discussing
    -0.09
    POSITIVE LOGITS
     detect
    0.17
     process
    0.17
     compute
    0.16
     store
    0.16
     handle
    0.16
     call
    0.16
     iterate
    0.15
     do
    0.14
     parse
    0.14
     perform
    0.14
    Activations Density 0.084%

    No Known Activations