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. 77200
    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
    Reading
    -0.08
    台
    -0.07
    中国特色社会主义
    -0.07
    人民币
    -0.07
    流水
    -0.07
     alkal
    -0.07
     NCAA
    -0.07
     languages
    -0.07
     reading
    -0.07
    oph
    -0.06
    POSITIVE LOGITS
     einf
    0.08
    ränkt
    0.08
    ’appr
    0.08
     unregister
    0.08
     حوالي
    0.08
    oreen
    0.08
    vlo
    0.08
     gc
    0.08
    eq
    0.08
    čí
    0.08
    Activations Density 0.000%

    No Known Activations