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. 120009
    Prev
    Next
    INDEX
    Explanations

    belong

    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
     Clover
    -0.08
     sert
    -0.08
     fen
    -0.08
     содержание
    -0.08
     खबर
    -0.07
     Chamb
    -0.07
     Davis
    -0.07
     nimi
    -0.07
     Dor
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    属于
    0.08
     belonged
    0.07
    -feature
    0.07
     belong
    0.07
    _RET
    0.07
     belongs
    0.07
    ileged
    0.07
    "class
    0.07
     Congreg
    0.07
    級
    0.07
    Activations Density 0.014%

    No Known Activations