Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77178
    Prev
    Next
    INDEX
    Explanations

    through

    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
    ế
    -0.08
     jewe
    -0.07
     detox
    -0.07
     apologize
    -0.07
     düz
    -0.07
     routines
    -0.07
    Failed
    -0.07
    scape
    -0.07
    유
    -0.07
    Routine
    -0.07
    POSITIVE LOGITS
     halfway
    0.09
     crossing
    0.09
     основания
    0.09
     niets
    0.08
    pring
    0.08
     Dart
    0.08
     Mittelpunkt
    0.08
     Bondye
    0.08
     IService
    0.08
     народа
    0.08
    Activations Density 0.018%

    No Known Activations