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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 119267
    Prev
    Next
    INDEX
    Explanations

    streets

    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
    لاج
    -0.08
     edging
    -0.08
    illot
    -0.07
    ುತ್ತ
    -0.07
    تە
    -0.07
    arms
    -0.07
     προηγ
    -0.07
     Schwerpunkt
    -0.07
     Arms
    -0.07
    HE
    -0.07
    POSITIVE LOGITS
     संघर्ष
    0.09
     bustling
    0.09
    pick
    0.08
    stro
    0.07
    冲
    0.07
     stro
    0.07
     Guided
    0.07
    andro
    0.07
     vigilant
    0.07
    duction
    0.07
    Activations Density 0.019%

    No Known Activations