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. 42098
    Prev
    Next
    INDEX
    Explanations

    Big Five

    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
     és
    -0.09
     Minist
    -0.08
    otoxic
    -0.08
     lourd
    -0.08
     accél
    -0.08
     ಮಗ
    -0.08
     superiority
    -0.08
     kidd
    -0.08
     Rapid
    -0.08
     prés
    -0.08
    POSITIVE LOGITS
     faca
    0.07
     fixture
    0.07
     fundamentales
    0.07
    NG
    0.07
    ZM
    0.07
    ेका
    0.07
     fundamental
    0.07
    Pitch
    0.07
    sv
    0.07
     שש
    0.07
    Activations Density 0.000%

    No Known Activations