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. 65868
    Prev
    Next
    INDEX
    Explanations

    Name

    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
     Ital
    -0.07
     Message
    -0.07
     uite
    -0.07
     бро
    -0.07
     Tennis
    -0.07
     �
    -0.07
     вс
    -0.07
     Вс
    -0.07
    (Message
    -0.07
     ات
    -0.07
    POSITIVE LOGITS
    Pham
    0.08
     opname
    0.08
     Guided
    0.08
    Beam
    0.08
    农村
    0.08
    Genes
    0.07
    Oid
    0.07
     beurre
    0.07
    Laravel
    0.07
     repayments
    0.07
    Activations Density 0.041%

    No Known Activations