© 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. 48531
    Prev
    Next
    INDEX
    Explanations

    N

    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
    amulka
    -0.10
    Faʻ
    -0.10
     ჩაი
    -0.10
    სი
    -0.10
    ალია
    -0.09
    ცია
    -0.09
     आएको
    -0.09
    ელმა
    -0.09
    liği
    -0.09
    ეთა
    -0.09
    POSITIVE LOGITS
    ikon
    0.18
     Nikon
    0.17
    okin
    0.14
    ikk
    0.13
    ik
    0.11
    IK
    0.11
     photographer
    0.11
     Kamera
    0.10
     nik
    0.10
    ok
    0.10
    Activations Density 0.000%

    No Known Activations