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. 44504
    Prev
    Next
    INDEX
    Explanations

    -(

    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
     SG
    -0.08
    �
    -0.08
     Kyr
    -0.08
    Xin
    -0.07
     βάση
    -0.07
     molten
    -0.07
    �
    -0.07
    รอง
    -0.07
     Cun
    -0.07
     Cura
    -0.07
    POSITIVE LOGITS
    quart
    0.08
    -community
    0.07
     ସ
    0.07
     esp
    0.07
     соз
    0.07
     સમ
    0.07
    掉
    0.07
     হল
    0.07
    �
    0.07
    /rest
    0.07
    Activations Density 0.012%

    No Known Activations