© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2766
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dient
    -0.08
     如
    -0.08
     déf
    -0.08
    ycl
    -0.08
    IDTH
    -0.08
    idth
    -0.08
    adrat
    -0.07
    agr
    -0.07
     PL
    -0.07
     Voc
    -0.07
    POSITIVE LOGITS
     indi
    0.08
    Asc
    0.08
     counterfeit
    0.08
     способов
    0.08
     sightings
    0.07
     оди
    0.07
    群众
    0.07
     inadvert
    0.07
    -speaking
    0.07
     sight
    0.07
    Activations Density 0.062%

    No Known Activations