© 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. 99269
    Prev
    Next
    INDEX
    Explanations

    of

    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
    .DTO
    -0.08
     pasado
    -0.08
    .pass
    -0.08
    .scheme
    -0.08
    ktions
    -0.08
     pasó
    -0.08
    .has
    -0.07
    .contains
    -0.07
    Example
    -0.07
    Gir
    -0.07
    POSITIVE LOGITS
     ολο
    0.10
     tevreden
    0.09
    满意
    0.09
     фин
    0.09
     ulg
    0.08
     finition
    0.08
     时时
    0.08
    ností
    0.08
     finalize
    0.08
     продолж
    0.08
    Activations Density 0.001%

    No Known Activations