© 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. 23-RESID-POST-AA
    11. 51176
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beaucoup
    -0.10
     Much
    -0.09
    much
    -0.09
     sedang
    -0.09
    Much
    -0.09
     molto
    -0.09
    :/
    -0.08
    .:
    -0.08
    ‍:
    -0.08
     veel
    -0.08
    POSITIVE LOGITS
     desto
    0.25
     càng
    0.17
    越
    0.16
     вероятность
    0.15
     the
    0.14
     semakin
    0.13
     steigt
    0.13
     chances
    0.13
     merr
    0.12
     likelihood
    0.12
    Activations Density 0.036%

    No Known Activations