© 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. 19-RESID-POST-AA
    11. 18506
    Prev
    Next
    INDEX
    Explanations

    say "edges"

    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
     societies
    -0.09
    Persona
    -0.09
     Persona
    -0.09
     Paulo
    -0.09
     Prezident
    -0.09
     Potion
    -0.09
     Palestinians
    -0.09
     psik
    -0.09
     Pessoa
    -0.09
     horoscope
    -0.09
    POSITIVE LOGITS
     edges
    0.22
    _edges
    0.21
    edges
    0.19
    Edges
    0.19
     edge
    0.18
    .edges
    0.17
    edge
    0.17
    _edge
    0.16
    (edges
    0.16
    -edge
    0.16
    Activations Density 0.023%

    No Known Activations