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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99110
    Prev
    Next
    INDEX
    Explanations

    game development

    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
     devotion
    -0.09
     filial
    -0.08
     virtues
    -0.08
     sterling
    -0.08
     comfortably
    -0.08
    comfortable
    -0.08
     confortável
    -0.08
     cozy
    -0.08
     appealed
    -0.08
     philosophy
    -0.08
    POSITIVE LOGITS
    /random
    0.12
    .random
    0.12
     infest
    0.11
     randomness
    0.11
    .Random
    0.11
     randomly
    0.11
    Random
    0.11
    random
    0.11
    _random
    0.11
     intermitt
    0.11
    Activations Density 0.019%

    No Known Activations