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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29271
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
     faced
    -0.09
    _mean
    -0.08
    δρο
    -0.08
    aced
    -0.07
    _binding
    -0.07
    .D
    -0.07
     contempor
    -0.07
     statistically
    -0.07
    U
    -0.07
     Mort
    -0.07
    POSITIVE LOGITS
     exceed
    0.08
     få
    0.08
     ụfọdụ
    0.08
    范围
    0.08
     exceeded
    0.08
     alc
    0.08
    超过
    0.08
     unreachable
    0.08
     exced
    0.08
    ャ
    0.08
    Activations Density 0.026%

    No Known Activations