© 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. 49426
    Prev
    Next
    INDEX
    Explanations

    :

    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
    .input
    -0.12
    (input
    -0.10
     earlier
    -0.10
    121
    -0.10
     input
    -0.10
     여러
    -0.10
    199
    -0.09
    Multiple
    -0.09
    .INPUT
    -0.09
    .previous
    -0.09
    POSITIVE LOGITS
    wurf
    0.11
     рыш
    0.11
    qqut
    0.10
    qatig
    0.10
    qarp
    0.10
    Xana
    0.10
    arlugu
    0.10
    ურად
    0.10
    чнай
    0.10
    არჯ
    0.10
    Activations Density 0.010%

    No Known Activations