© 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. 50349
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Posté
    -0.08
    ۱۵
    -0.08
     stationed
    -0.08
    خاص
    -0.08
    ۲۰۱
    -0.08
     adda
    -0.08
    662
    -0.08
    798
    -0.08
     FONT
    -0.08
    _TASK
    -0.08
    POSITIVE LOGITS
    fty
    0.30
    finity
    0.25
    ∞
    0.23
     infinity
    0.21
    finite
    0.20
    Infinity
    0.19
     infinito
    0.18
     Infinity
    0.18
    FINITY
    0.16
    .infinity
    0.16
    Activations Density 0.011%

    No Known Activations