© 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. 70032
    Prev
    Next
    INDEX
    Explanations

    units and foreign "un"

    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
    -crafted
    -0.09
     Sunday's
    -0.08
     avantaj
    -0.08
    pattern
    -0.08
    Saturday
    -0.08
     Concierge
    -0.08
     못
    -0.08
    mallow
    -0.08
     médit
    -0.07
    Panel
    -0.07
    POSITIVE LOGITS
     units
    0.15
     Units
    0.13
    _units
    0.13
    Units
    0.13
    .units
    0.12
    units
    0.12
     unités
    0.12
     unidades
    0.11
    单位
    0.11
     volts
    0.10
    Activations Density 0.036%

    No Known Activations