© 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. 50462
    Prev
    Next
    INDEX
    Explanations

    -h

    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
    erdings
    -0.09
     Our
    -0.08
     våra
    -0.08
    oom
    -0.08
     rsp
    -0.08
     हमारा
    -0.08
     naszych
    -0.08
     nossa
    -0.08
     наша
    -0.08
     અમારા
    -0.08
    POSITIVE LOGITS
    andle
    0.12
    ash
    0.12
    yp
    0.11
    yper
    0.11
    istorical
    0.11
    arm
    0.10
    as
    0.10
    old
    0.10
    ar
    0.10
    umidity
    0.10
    Activations Density 0.005%

    No Known Activations