© 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. 11-RESID-POST-AA
    11. 63651
    Prev
    Next
    INDEX
    Explanations

    contract legal language

    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
     aangegeven
    -0.08
     adh
    -0.08
     indication
    -0.08
     aangeven
    -0.08
     מאוד
    -0.08
    യ്ക്ക്
    -0.07
     solver
    -0.07
     തന്ന
    -0.07
    科研
    -0.07
    以
    -0.07
    POSITIVE LOGITS
     profanity
    0.09
    phil
    0.08
     проста
    0.08
    lead
    0.08
    legte
    0.08
     Children
    0.08
    Leaves
    0.08
    Animal
    0.07
    /lib
    0.07
    Creature
    0.07
    Activations Density 0.011%

    No Known Activations