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. 119516
    Prev
    Next
    INDEX
    Explanations

    internal

    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
     упражнения
    -0.07
    -0.07
    -0.07
     cant
    -0.06
     koris
    -0.06
     you're
    -0.06
    �
    -0.06
    _address
    -0.06
     cin
    -0.06
    obooks
    -0.06
    POSITIVE LOGITS
     confidential
    0.12
    秘密
    0.11
     secretly
    0.10
     Confidential
    0.10
     ખાન
    0.10
     Bloomberg
    0.10
    	internal
    0.10
    _prior
    0.10
     secr
    0.10
     privately
    0.10
    Activations Density 0.274%

    No Known Activations