© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 49242
    Prev
    Next
    INDEX
    Explanations

    ske

    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
    ਾਈ
    -0.09
    ಾವಣೆ
    -0.09
    ਾਇ
    -0.08
    ಾವಣ
    -0.08
    -around
    -0.08
    yada
    -0.07
     Leistung
    -0.07
    ajn
    -0.07
    авис
    -0.07
     erbyn
    -0.07
    POSITIVE LOGITS
    letal
    0.16
    ptic
    0.15
    chers
    0.12
    pt
    0.11
    letics
    0.11
    PT
    0.11
    let
    0.11
    ప్ట
    0.11
    leta
    0.11
    eter
    0.10
    Activations Density 0.001%

    No Known Activations