© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29502
    Prev
    Next
    INDEX
    Explanations

    percent

    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
    URATION
    -0.08
     spod
    -0.07
    (Project
    -0.07
    .the
    -0.07
     scén
    -0.07
     зел
    -0.07
     dirig
    -0.07
     Harvard
    -0.07
    WARE
    -0.07
     benchmarking
    -0.07
    POSITIVE LOGITS
     धीरे
    0.09
     effortless
    0.09
     변화
    0.09
     بسيطة
    0.08
     발전
    0.08
     gradual
    0.08
    changes
    0.08
    bite
    0.08
     చిన్న
    0.08
     대비
    0.08
    Activations Density 0.004%

    No Known Activations