© 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. 11-RESID-POST-AA
    11. 112438
    Prev
    Next
    INDEX
    Explanations

    corpus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íp
    -0.08
     messing
    -0.08
     乐
    -0.08
     madd
    -0.08
     zig
    -0.08
     pés
    -0.08
    仙
    -0.07
     fez
    -0.07
    ിപ
    -0.07
     hammered
    -0.07
    POSITIVE LOGITS
     corpus
    0.15
     corp
    0.12
    Corpus
    0.10
     Corpus
    0.09
     samples
    0.09
    orpus
    0.08
     확보
    0.08
     vocab
    0.08
    یر
    0.08
    资料
    0.08
    Activations Density 0.003%

    No Known Activations