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. 54419
    Prev
    Next
    INDEX
    Explanations

    Legends and stories

    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
     Tahoe
    -0.08
     Edmond
    -0.08
    емый
    -0.08
    blk
    -0.08
    elder
    -0.08
    —a
    -0.07
     Jehova
    -0.07
    той
    -0.07
    ása
    -0.07
     alba
    -0.07
    POSITIVE LOGITS
    Bir
    0.09
     supaya
    0.08
     प्लेट
    0.08
     يقع
    0.08
     sehingga
    0.08
    _ALLOWED
    0.08
    .RE
    0.08
     причины
    0.08
    opin
    0.08
     Bir
    0.08
    Activations Density 0.000%

    No Known Activations