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. 49190
    Prev
    Next
    INDEX
    Explanations

    accented characters

    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
    /se
    -0.08
     Nak
    -0.08
     Dick
    -0.08
    оч
    -0.08
     CUT
    -0.08
     Commissioner
    -0.07
     arena
    -0.07
     Chase
    -0.07
     Kill
    -0.07
     shred
    -0.07
    POSITIVE LOGITS
    tar
    0.08
    Tin
    0.08
    lb
    0.08
    0.07
    coal
    0.07
     quartet
    0.07
    熟
    0.07
    బడ
    0.07
    larni
    0.07
    变
    0.07
    Activations Density 0.005%

    No Known Activations