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. 65494
    Prev
    Next
    INDEX
    Explanations

    thickness

    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
     উঠে
    -0.09
     मौ
    -0.09
    vatore
    -0.08
     ಬೇ
    -0.08
     crimin
    -0.08
     तत्काल
    -0.08
    çadas
    -0.07
    டிய
    -0.07
     чем
    -0.07
    752
    -0.07
    POSITIVE LOGITS
    是多少
    0.08
     reka
    0.07
    -pref
    0.07
     chim
    0.07
    .Tag
    0.07
     ness
    0.07
    Casa
    0.07
    度
    0.07
     slab
    0.07
     preferably
    0.07
    Activations Density 0.004%

    No Known Activations