© 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. 96830
    Prev
    Next
    INDEX
    Explanations

    Describing different contexts

    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
    supported
    -0.09
    Supported
    -0.08
    parameters
    -0.08
     auxiliary
    -0.08
    -0.08
    Mechan
    -0.08
    増
    -0.07
    aux
    -0.07
     supported
    -0.07
     utilized
    -0.07
    POSITIVE LOGITS
    场
    0.28
    情
    0.26
    場合
    0.24
     సందర్భ
    0.23
     സാഹചര്യ
    0.23
     情
    0.22
     ಸಂದರ್ಭ
    0.21
    情况下
    0.21
    場
    0.21
    情况
    0.20
    Activations Density 0.044%
    No Known Activations