© 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. 63986
    Prev
    Next
    INDEX
    Explanations

    is

    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
    iid
    -0.08
    ,n
    -0.07
    Ing
    -0.07
    029
    -0.07
    -cons
    -0.07
    122
    -0.07
    176
    -0.07
    ல்ல
    -0.07
    НИ
    -0.07
    124
    -0.07
    POSITIVE LOGITS
     gritty
    0.11
     unpleasant
    0.09
     horrible
    0.09
     grit
    0.09
     disgusting
    0.09
     franchement
    0.09
     Kitty
    0.08
     vị
    0.08
     downright
    0.08
     Marines
    0.08
    Activations Density 0.008%

    No Known Activations