© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99358
    Prev
    Next
    INDEX
    Explanations

    ilian

    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
    aptic
    -0.08
     सभ
    -0.07
     तैयार
    -0.07
    phot
    -0.07
    Petit
    -0.07
     tenure
    -0.07
    position
    -0.07
     दृ
    -0.07
    _pose
    -0.07
     parche
    -0.07
    POSITIVE LOGITS
     concede
    0.09
    .solution
    0.08
     soli
    0.08
     cleanse
    0.08
     bunt
    0.08
     pointless
    0.08
     gezocht
    0.08
     Promotional
    0.08
     kanilang
    0.08
     COLORS
    0.08
    Activations Density 0.001%

    No Known Activations