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. 77495
    Prev
    Next
    INDEX
    Explanations

    mos

    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
     son
    -0.07
     término
    -0.07
     principle
    -0.07
     forma
    -0.07
    UNITY
    -0.07
    алық
    -0.07
    Indiana
    -0.07
     phrase
    -0.07
    61
    -0.07
    _stat
    -0.07
    POSITIVE LOGITS
     словно
    0.09
     swirling
    0.08
     вечером
    0.08
    ക്കും
    0.08
     surrounding
    0.08
     徐
    0.08
     постепенно
    0.08
     eraill
    0.08
    Mist
    0.08
    МК
    0.08
    Activations Density 0.017%

    No Known Activations