© 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. 23-RESID-POST-AA
    11. 51442
    Prev
    Next
    INDEX
    Explanations

    -

    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
    -point
    -0.11
    -face
    -0.10
    -sector
    -0.10
    -tone
    -0.10
    -name
    -0.10
    -level
    -0.10
    -tier
    -0.10
    -colored
    -0.09
    -year
    -0.09
    -size
    -0.09
    POSITIVE LOGITS
     distance
    0.12
     distancia
    0.11
     Distance
    0.11
     afstand
    0.11
     awaited
    0.11
     दूरी
    0.11
    .Distance
    0.11
    .Last
    0.11
    distance
    0.11
    lasting
    0.11
    Activations Density 0.005%

    No Known Activations