© 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. 49575
    Prev
    Next
    INDEX
    Explanations

    say the ending -aining, -ains, -ain, or -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
    ummed
    -0.09
    um
    -0.08
    unku
    -0.08
    upuncture
    -0.08
    unch
    -0.08
    unn
    -0.08
    unched
    -0.08
    ంక
    -0.08
    ंका
    -0.08
    ُن
    -0.07
    POSITIVE LOGITS
    aining
    0.36
    ained
    0.36
    ain
    0.35
    ains
    0.33
    AIN
    0.28
    ainment
    0.26
    ainers
    0.25
    ainer
    0.25
    েই
    0.21
    aina
    0.20
    Activations Density 0.022%

    No Known Activations