© 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. 49356
    Prev
    Next
    INDEX
    Explanations

    :l

    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
     prize
    -0.08
     lado
    -0.08
    ోగ
    -0.08
    ोग
    -0.07
     бак
    -0.07
     getattr
    -0.07
    tooltip
    -0.07
     tooltip
    -0.07
    QP
    -0.07
    πο
    -0.07
    POSITIVE LOGITS
    ifecycle
    0.12
    if
    0.10
     Wohl
    0.08
     Roh
    0.08
    Lifecycle
    0.08
    Ví
    0.07
    bonne
    0.07
    ifton
    0.07
    .dk
    0.07
    aal
    0.07
    Activations Density 0.000%

    No Known Activations