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. 58308
    Prev
    Next
    INDEX
    Explanations

    fine

    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
     Sticky
    -0.08
    .echo
    -0.08
    ാവ
    -0.07
     hung
    -0.07
     sticky
    -0.07
     sanctuary
    -0.07
     tragedies
    -0.07
     Regardless
    -0.07
    -0.07
     Org
    -0.07
    POSITIVE LOGITS
     excepto
    0.13
     except
    0.12
     większo
    0.12
    except
    0.12
     अधिकांश
    0.11
     soweit
    0.11
     معظم
    0.11
     mostly
    0.11
     maioria
    0.11
     الحمد
    0.10
    Activations Density 0.127%

    No Known Activations