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. 11836
    Prev
    Next
    INDEX
    Explanations

    through

    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
    รู้
    -0.08
    aneous
    -0.08
     textual
    -0.07
    roepen
    -0.07
     significativo
    -0.07
    epoch
    -0.07
     epoch
    -0.07
     significado
    -0.07
     resa
    -0.07
    태
    -0.07
    POSITIVE LOGITS
    -hole
    0.09
     hole
    0.09
     warped
    0.08
    hall
    0.08
    -br
    0.08
    Walls
    0.08
    helmet
    0.08
     отверст
    0.08
     ворот
    0.08
     नर
    0.08
    Activations Density 0.016%

    No Known Activations