© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7975
    Prev
    Next
    INDEX
    Explanations

    science education materials

    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
     Lon
    -0.08
    .metrics
    -0.08
     прос
    -0.08
    �
    -0.08
     precision
    -0.08
     dezenas
    -0.08
    业内
    -0.07
    rotechn
    -0.07
     sensitiv
    -0.07
    metrics
    -0.07
    POSITIVE LOGITS
     الأشياء
    0.09
     magician
    0.09
    Hindi
    0.09
    hidden
    0.09
    _barang
    0.08
     slideshow
    0.08
     Hindi
    0.08
     zichtbaar
    0.08
     მოძრაობ
    0.08
     კომენტ
    0.08
    Activations Density 0.024%

    No Known Activations