© 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. 50273
    Prev
    Next
    INDEX
    Explanations

    Width and height

    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
     الرسول
    -0.11
     árbit
    -0.09
     Dial
    -0.09
     صلى
    -0.09
     Punk
    -0.09
     Flughafen
    -0.09
     kuru
    -0.08
     بشأن
    -0.08
     clichés
    -0.08
     señaló
    -0.08
    POSITIVE LOGITS
     width
    0.28
     height
    0.25
    _width
    0.25
     widths
    0.24
    Width
    0.24
     heights
    0.24
    height
    0.24
    width
    0.24
    (width
    0.23
    .width
    0.23
    Activations Density 0.067%

    No Known Activations