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. 49223
    Prev
    Next
    INDEX
    Explanations

    into

    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
    스럽
    -0.07
    raut
    -0.07
    deren
    -0.07
    året
    -0.07
     lên
    -0.07
    ёв
    -0.07
    aski
    -0.07
     сами
    -0.07
     microscopy
    -0.07
    woo
    -0.07
    POSITIVE LOGITS
     arbor
    0.08
    Parts
    0.08
    622
    0.08
     blocks
    0.07
    121
    0.07
     separate
    0.07
     actionable
    0.07
    یره
    0.07
    928
    0.07
     insol
    0.07
    Activations Density 0.021%

    No Known Activations