© 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. 19-RESID-POST-AA
    11. 21222
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdin
    -0.08
     każde
    -0.08
    each
    -0.08
     fiecare
    -0.08
    zeros
    -0.08
    nothing
    -0.08
    zero
    -0.08
     لكل
    -0.08
     Each
    -0.08
     Cada
    -0.08
    POSITIVE LOGITS
    _length
    0.17
     length
    0.16
     дли
    0.16
     Length
    0.15
    Length
    0.15
    长度
    0.15
    	length
    0.15
     lenght
    0.15
     lengte
    0.14
    _LENGTH
    0.14
    Activations Density 0.032%

    No Known Activations