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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49768
    Prev
    Next
    INDEX
    Explanations

    EOF

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ↵        ↵
    -0.10
    fires
    -0.09
     ↵		↵
    -0.09
    viewer
    -0.08
     Strength
    -0.08
    strength
    -0.08
    üler
    -0.08
     Fires
    -0.08
     Throws
    -0.08
     Eine
    -0.07
    POSITIVE LOGITS
    ="↵
    0.10
    George
    0.10
     quay
    0.10
    ="
    0.09
    =yes
    0.09
    'expérience
    0.09
    ="./
    0.09
    .reactivex
    0.08
    =""></
    0.08
     عاد
    0.08
    Activations Density 0.001%

    No Known Activations