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. 12672
    Prev
    Next
    INDEX
    Explanations

    everyone

    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
    ト
    -0.07
    سى
    -0.07
    trag
    -0.07
     Wright
    -0.07
     Rah
    -0.07
    Shock
    -0.07
     место
    -0.07
     Shock
    -0.07
    car
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     else's
    0.11
    에게
    0.11
    -orang
    0.11
    一样
    0.09
    们
    0.09
     omkring
    0.09
     원하는
    0.09
     Gel
    0.09
    Gel
    0.08
    هاد
    0.08
    Activations Density 0.067%

    No Known Activations