Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11778
    Prev
    Next
    INDEX
    Explanations

    code

    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
     reinvent
    -0.08
    �
    -0.08
     sinal
    -0.08
     concursos
    -0.08
    ั่น
    -0.07
     સંપ
    -0.07
     concurso
    -0.07
    Prescription
    -0.07
    Cod
    -0.07
    azos
    -0.07
    POSITIVE LOGITS
     शाख
    0.10
     Diagram
    0.10
     Branch
    0.10
     UML
    0.09
     branching
    0.09
     depicted
    0.09
     branches
    0.09
     Gupta
    0.09
     Tooltip
    0.08
     Belgique
    0.08
    Activations Density 0.005%

    No Known Activations