© 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. 50492
    Prev
    Next
    INDEX
    Explanations

    description

    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
     voorzichtig
    -0.08
     պայման
    -0.08
    גענ
    -0.08
     հաշ
    -0.07
     որոշ
    -0.07
     sorgfält
    -0.07
    ...")↵
    -0.07
     осторож
    -0.07
     ...)↵
    -0.07
     stabilization
    -0.07
    POSITIVE LOGITS
     ready
    0.24
    ready
    0.22
     usable
    0.21
     Ready
    0.19
    Ready
    0.19
     suitable
    0.19
    _ready
    0.18
    .ready
    0.18
    用于
    0.18
    -ready
    0.18
    Activations Density 0.187%

    No Known Activations