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

    Neuronpedia

    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. 103293
    Prev
    Next
    INDEX
    Explanations

    dip

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -0.09
    ులతో
    -0.07
     साथ
    -0.07
    429
    -0.07
     who
    -0.07
    oarthritis
    -0.07
    on
    -0.07
     supporting
    -0.07
    との
    -0.07
     beating
    -0.07
    POSITIVE LOGITS
     immerse
    0.19
     immersion
    0.18
     immersed
    0.18
     submerged
    0.17
     Immer
    0.16
    Immer
    0.16
     dipped
    0.16
     immers
    0.15
     plong
    0.15
     plonge
    0.15
    Activations Density 0.010%

    No Known Activations