© 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. 49960
    Prev
    Next
    INDEX
    Explanations

    say "orse" word

    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
    isor
    -0.08
    DDS
    -0.07
     действие
    -0.07
    .CONTENT
    -0.07
    Indicators
    -0.07
     happen
    -0.07
     development
    -0.07
     happens
    -0.07
    <Action
    -0.07
     kedua
    -0.07
    POSITIVE LOGITS
    orse
    0.09
     varie
    0.08
    abili
    0.08
     wides
    0.08
    virtió
    0.08
     ve
    0.07
     varies
    0.07
    ্ৰী
    0.07
     قدرة
    0.07
     Regiment
    0.07
    Activations Density 0.000%

    No Known Activations