© 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. 50744
    Prev
    Next
    INDEX
    Explanations

    Japanese/Korean character

    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
    elligent
    -0.08
    entials
    -0.08
    ellite
    -0.08
    anded
    -0.08
    uram
    -0.08
    onin
    -0.08
    stripe
    -0.07
    attice
    -0.07
    elligence
    -0.07
    rench
    -0.07
    POSITIVE LOGITS
    モ
    0.15
    ッ
    0.15
    ニュー
    0.13
    ಮೊ
    0.11
    کان
    0.11
    タ
    0.10
    ன்ப
    0.10
    ーカ
    0.10
    ジャ
    0.10
    イン
    0.10
    Activations Density 0.000%

    No Known Activations