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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103622
    Prev
    Next
    INDEX
    Explanations

    Algorithm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foundational
    -0.10
     encompassing
    -0.09
     شکار
    -0.09
     Այս
    -0.09
     հնարավորություն
    -0.09
     یوې
    -0.09
    ritra
    -0.08
    focused
    -0.08
     qauv
    -0.08
     kës
    -0.08
    POSITIVE LOGITS
     Steps
    0.14
     steps
    0.13
    Steps
    0.12
    _steps
    0.12
     Outline
    0.11
     itself
    0.11
    steps
    0.11
     outline
    0.11
     proceeds
    0.10
    Outline
    0.10
    Activations Density 0.005%

    No Known Activations