© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49283
    Prev
    Next
    INDEX
    Explanations

    Foreign language references

    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
    ाई
    -0.08
     Named
    -0.08
    Named
    -0.08
    ark
    -0.07
    ied
    -0.07
     reason
    -0.07
     Tang
    -0.07
     tup
    -0.07
    .length
    -0.07
    446
    -0.07
    POSITIVE LOGITS
    цара
    0.13
    цар
    0.11
    стю
    0.09
    igende
    0.09
    querque
    0.09
    σεων
    0.09
    cić
    0.09
    իչ
    0.09
    igings
    0.09
    igens
    0.09
    Activations Density 0.008%

    No Known Activations