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. 44246
    Prev
    Next
    INDEX
    Explanations

    Queue

    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
     तिच
    -0.08
     t
    -0.08
     Graz
    -0.08
     jej
    -0.08
    (delete
    -0.08
    บน
    -0.07
     isikhathi
    -0.07
    翼
    -0.07
     її
    -0.07
    (stop
    -0.07
    POSITIVE LOGITS
     categorical
    0.08
     blatant
    0.08
     rikt
    0.07
     improper
    0.07
     Cornell
    0.07
    0.07
    verm
    0.07
     '&#
    0.07
     plut
    0.07
     ytter
    0.07
    Activations Density 0.000%

    No Known Activations