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. 111651
    Prev
    Next
    INDEX
    Explanations

    demand

    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
     ribbons
    -0.09
     Fuji
    -0.08
     saada
    -0.08
     ribbon
    -0.08
    Inheritance
    -0.08
     Pig
    -0.07
    .FILE
    -0.07
    ygons
    -0.07
     Pel
    -0.07
     murals
    -0.07
    POSITIVE LOGITS
     Bedarf
    0.09
     મુજબ
    0.08
    }@
    0.08
     સમયે
    0.08
     માંગ
    0.08
     نیاز
    0.07
     Bundes
    0.07
    라인
    0.07
    ообраз
    0.07
     verfügbar
    0.07
    Activations Density 0.009%

    No Known Activations