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. 61049
    Prev
    Next
    INDEX
    Explanations

    Image generation commands

    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
     सामना
    -0.08
    abeh
    -0.08
    _THRESHOLD
    -0.08
     pay
    -0.08
    €↵
    -0.08
    sgál
    -0.08
     rental
    -0.08
    €,
    -0.08
    赖
    -0.07
    没
    -0.07
    POSITIVE LOGITS
     sentence
    0.07
     phrases
    0.07
     Paragraph
    0.07
     مكان
    0.07
     Fancy
    0.07
     Suddenly
    0.07
     Immediately
    0.07
     Sentence
    0.07
     کلی
    0.07
     Content
    0.07
    Activations Density 0.003%

    No Known Activations