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. 117469
    Prev
    Next
    INDEX
    Explanations

    by

    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
    Domains
    -0.09
    ებელი
    -0.08
    _domains
    -0.08
    üml
    -0.08
     Domains
    -0.08
     Shay
    -0.08
     Strict
    -0.08
     Sert
    -0.08
    ებულ
    -0.08
     ملايين
    -0.07
    POSITIVE LOGITS
     vanished
    0.08
     vanish
    0.07
     killed
    0.07
     নির্বাচন
    0.07
    ktor
    0.07
    BX
    0.07
    theta
    0.07
     doorway
    0.07
     likeness
    0.07
     क्योंकि
    0.07
    Activations Density 0.038%

    No Known Activations