© 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. 19-RESID-POST-AA
    11. 22153
    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
    -ass
    -0.09
    /prom
    -0.08
    /ge
    -0.08
    /by
    -0.08
     specif
    -0.08
    /how
    -0.08
    -met
    -0.08
    /year
    -0.08
     weyn
    -0.08
     fà
    -0.08
    POSITIVE LOGITS
     боломж
    0.09
     способны
    0.09
     какие
    0.09
     관련
    0.08
     никаких
    0.08
     словно
    0.08
     желуд
    0.08
     срав
    0.08
     비교
    0.08
    enticated
    0.08
    Activations Density 0.010%

    No Known Activations