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. 422
    Prev
    Next
    INDEX
    Explanations

    |

    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
    ที่จะ
    -0.08
    enger
    -0.07
     مول
    -0.07
    От
    -0.07
     Iglesia
    -0.07
    ‑
    -0.07
     mert
    -0.07
    .alg
    -0.07
     Mirrors
    -0.07
     Berger
    -0.07
    POSITIVE LOGITS
     erection
    0.08
     hingegen
    0.08
     eher
    0.08
     nə
    0.08
     Regency
    0.08
     Arial
    0.07
     unequiv
    0.07
    多少
    0.07
     roten
    0.07
     sympathetic
    0.07
    Activations Density 0.133%

    No Known Activations