© 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. 20947
    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
    通常
    -0.09
     അവരുടെ
    -0.09
    [N
    -0.08
    普
    -0.08
    their
    -0.08
    Their
    -0.08
    [position
    -0.08
    ਿਆਂ
    -0.08
    Explicit
    -0.08
    Implicit
    -0.08
    POSITIVE LOGITS
     resembles
    0.19
     resemble
    0.17
     reminiscent
    0.17
     ressemble
    0.16
     resembling
    0.16
     resemblance
    0.15
     ressembl
    0.15
     German
    0.14
     похож
    0.14
     Gaelic
    0.14
    Activations Density 0.041%

    No Known Activations