© 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 EvalsExportsinterp-engineNEWAPI 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. 63094
    Prev
    Next
    INDEX
    Explanations

    Research studies

    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
     hazards
    -0.09
    EJB
    -0.09
     riscos
    -0.08
     accolades
    -0.08
     yards
    -0.08
     radiator
    -0.08
     changer
    -0.08
    事故
    -0.07
     agh
    -0.07
    .maven
    -0.07
    POSITIVE LOGITS
     cortical
    0.13
     EEG
    0.12
     schizophrenia
    0.10
     cortic
    0.10
     neurons
    0.10
     corticost
    0.10
     neuronal
    0.09
     transcription
    0.09
     cortex
    0.09
     malad
    0.09
    Activations Density 0.010%

    No Known Activations