© 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 EvalsExportsinterp-engineNEWAPI 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. 71172
    Prev
    Next
    INDEX
    Explanations

    phosphorylation

    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
     Trophy
    -0.08
     trophy
    -0.08
     termite
    -0.07
     hum
    -0.07
    spel
    -0.07
    ikken
    -0.07
    窝
    -0.07
    صيد
    -0.07
    Tim
    -0.07
     comércio
    -0.07
    POSITIVE LOGITS
    /un
    0.10
    esk
    0.07
     Ska
    0.07
    /de
    0.07
    (None
    0.07
    (acc
    0.07
    (Reg
    0.07
    'ing
    0.07
     produced
    0.07
    397
    0.07
    Activations Density 0.001%

    No Known Activations