Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65666
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ,但是
    -0.09
     Hone
    -0.08
     Able
    -0.08
     ABB
    -0.08
     zwar
    -0.08
     Tala
    -0.08
     असून
    -0.08
     Million
    -0.08
     Curse
    -0.08
    NER
    -0.08
    POSITIVE LOGITS
     dichos
    0.08
    !</
    0.07
     unsus
    0.07
     Edmond
    0.07
     suitably
    0.07
     supl
    0.07
     ever
    0.07
     fol
    0.07
    thumb
    0.07
    .</
    0.07
    Activations Density 0.484%

    No Known Activations