© 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. 113356
    Prev
    Next
    INDEX
    Explanations

    \

    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
     overlooking
    -0.09
     testemun
    -0.08
     flotation
    -0.08
    endium
    -0.08
    _float
    -0.08
     buoy
    -0.08
    休
    -0.08
     motivatie
    -0.07
    flammatory
    -0.07
     nhìn
    -0.07
    POSITIVE LOGITS
    -compose
    0.12
     compositions
    0.11
     функций
    0.11
     composition
    0.10
     compose
    0.10
     functions
    0.10
    Performed
    0.10
     funcs
    0.09
     Funktionen
    0.09
     funciones
    0.09
    Activations Density 0.040%

    No Known Activations