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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97202
    Prev
    Next
    INDEX
    Explanations

    pair

    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
     Μέ
    -0.09
     unserem
    -0.08
     unseren
    -0.08
     جاري
    -0.08
     localizada
    -0.07
     ubicada
    -0.07
    assat
    -0.07
    .hy
    -0.07
     "~/
    -0.07
     Bereits
    -0.07
    POSITIVE LOGITS
     pair
    0.22
     pairs
    0.22
    Pair
    0.21
     Pair
    0.21
    _pair
    0.20
    pair
    0.19
    _pairs
    0.19
    Pairs
    0.19
    pairs
    0.19
    (pair
    0.18
    Activations Density 0.132%

    No Known Activations