© 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. 26608
    Prev
    Next
    INDEX
    Explanations

    Cross

    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
     sluggish
    -0.08
     persuade
    -0.08
    จัด
    -0.08
     தேர்த
    -0.07
    ุน
    -0.07
    inem
    -0.07
    asional
    -0.07
     diput
    -0.07
    और
    -0.07
    েশ
    -0.07
    POSITIVE LOGITS
    -cross
    0.10
    -shaped
    0.10
     crosses
    0.10
     crossed
    0.09
     отмет
    0.09
     крест
    0.09
     crossroads
    0.08
    .Cross
    0.08
    _cross
    0.08
     Jerusalem
    0.08
    Activations Density 0.012%

    No Known Activations