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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113007
    Prev
    Next
    INDEX
    Explanations

    I

    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
    )V
    -0.08
    .).
    -0.07
     rhetorical
    -0.07
    ་�
    -0.07
    経
    -0.07
    _vec
    -0.07
     периода
    -0.07
     symbol
    -0.07
    Temps
    -0.07
     patrons
    -0.07
    POSITIVE LOGITS
     лік
    0.10
     смерт
    0.08
     зді
    0.08
     онда
    0.08
     जग
    0.08
     tror
    0.08
     трав
    0.08
    hibernate
    0.08
     наказ
    0.08
     ụwa
    0.08
    Activations Density 0.007%

    No Known Activations