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

    Neuronpedia

    Jacobian LensNEW
    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. 69162
    Prev
    Next
    INDEX
    Explanations

    emerged

    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
    outer
    -0.08
    aca
    -0.08
    ecc
    -0.07
     जन
    -0.07
     nitr
    -0.07
                    ↵
    -0.07
    eraa
    -0.07
     Valentino
    -0.07
    -0.07
     Nah
    -0.07
    POSITIVE LOGITS
     espont
    0.08
     Miner
    0.08
    Seal
    0.08
     pains
    0.08
     Muster
    0.08
     wer
    0.08
     dub
    0.07
     retrieving
    0.07
    trend
    0.07
     gir
    0.07
    Activations Density 0.008%
    No Known Activations