© 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. 65507
    Prev
    Next
    INDEX
    Explanations

    ul

    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
     vocab
    -0.09
     groceries
    -0.09
     clips
    -0.08
    еред
    -0.08
     Aim
    -0.08
     закреп
    -0.08
     pack
    -0.08
     vocabulary
    -0.08
     aiming
    -0.08
     حفظ
    -0.08
    POSITIVE LOGITS
    -hidden
    0.09
    隐藏
    0.09
     hidden
    0.08
    戴
    0.08
    hidden
    0.08
     awak
    0.08
     invisible
    0.08
    מת
    0.08
     awakened
    0.08
    Waiting
    0.08
    Activations Density 0.001%

    No Known Activations