© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75545
    Prev
    Next
    INDEX
    Explanations

    long words

    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
     conver
    -0.08
     incub
    -0.08
    .usermodel
    -0.07
     teme
    -0.07
    逸
    -0.07
     hubungan
    -0.07
     alguns
    -0.07
     indépend
    -0.07
    家庭
    -0.07
     todo
    -0.07
    POSITIVE LOGITS
     lengthy
    0.13
     gigantic
    0.12
     длин
    0.11
     longest
    0.11
     ridiculously
    0.11
     विशाल
    0.10
     enormous
    0.10
     enorm
    0.10
     towering
    0.10
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.10
    Activations Density 0.022%

    No Known Activations