© 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. 113418
    Prev
    Next
    INDEX
    Explanations

    height and coordinates in code

    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
     oro
    -0.08
     PUR
    -0.08
    Cross
    -0.08
    Contr
    -0.07
    Coll
    -0.07
    fox
    -0.07
    Est
    -0.07
    ipro
    -0.07
     madr
    -0.07
     Lind
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.11
    ，以及
    0.10
     എന്നിവ
    0.09
    以及
    0.09
     그리고
    0.09
     oraz
    0.08
     എന്നീ
    0.08
    そして
    0.08
     tarih
    0.08
     என்ற
    0.08
    Activations Density 0.027%

    No Known Activations