© 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. 96683
    Prev
    Next
    INDEX
    Explanations

    hur

    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
    中华人民共和国
    -0.08
    ног
    -0.08
    როს
    -0.08
    EGIN
    -0.08
    busy
    -0.08
    人民共和国
    -0.08
    IDTH
    -0.07
    china
    -0.07
    -0.07
    egin
    -0.07
    POSITIVE LOGITS
    wenen
    0.11
    acán
    0.11
    witz
    0.10
    lfriend
    0.08
    akoa
    0.08
     wf
    0.08
    .ff
    0.08
    dl
    0.08
     Fx
    0.08
    フ�
    0.08
    Activations Density 0.002%
    No Known Activations