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. 11599
    Prev
    Next
    INDEX
    Explanations

    Image generation prompts

    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
     effectuer
    -0.08
    ורים
    -0.07
     unattended
    -0.07
    ongo
    -0.07
    ర్�
    -0.07
    ordnung
    -0.07
     DSS
    -0.07
    FAA
    -0.07
     continuously
    -0.07
    reducers
    -0.07
    POSITIVE LOGITS
     Judah
    0.09
     ▲
    0.07
    ▄
    0.07
     店
    0.07
     احترام
    0.07
     Wyatt
    0.07
     випад
    0.07
     Reads
    0.07
    blockquote
    0.07
     كثيرة
    0.07
    Activations Density 0.009%

    No Known Activations