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. 111674
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ๆ
    -0.10
     получается
    -0.08
    Bindable
    -0.08
    ్ష
    -0.08
     попрос
    -0.08
     סיפ
    -0.08
     понять
    -0.07
     afterward
    -0.07
    ácil
    -0.07
    emaking
    -0.07
    POSITIVE LOGITS
     Env
    0.08
     relatório
    0.08
     characterization
    0.07
    μός
    0.07
    ক্ষ
    0.07
    বার
    0.07
    Till
    0.07
    wehr
    0.07
    истан
    0.07
     welt
    0.07
    Activations Density 0.002%

    No Known Activations