© 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. 731
    Prev
    Next
    INDEX
    Explanations

    pre-commit hooks

    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
     treatment
    -0.08
     Treatment
    -0.08
    visited
    -0.07
     pairs
    -0.07
    _vis
    -0.07
     parentheses
    -0.07
    viz
    -0.07
    ియ
    -0.07
     segments
    -0.07
    ouses
    -0.07
    POSITIVE LOGITS
    -before
    0.11
    .prevent
    0.10
     sebelum
    0.10
     ennen
    0.09
    Before
    0.09
     BEFORE
    0.09
     禁
    0.09
     kafin
    0.09
     আগে
    0.09
     mora
    0.09
    Activations Density 0.002%

    No Known Activations