© 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. 102154
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment

    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
     booster
    -0.09
     joie
    -0.08
     alegría
    -0.08
     жив
    -0.08
     augmenter
    -0.08
     boost
    -0.08
     성공
    -0.08
    动态
    -0.08
     улыб
    -0.08
     ansch
    -0.08
    POSITIVE LOGITS
     bearish
    0.16
     downturn
    0.13
     negative
    0.12
     negatieve
    0.12
    -down
    0.12
     negativos
    0.12
    _negative
    0.12
     Negative
    0.12
    negative
    0.12
    Negative
    0.11
    Activations Density 0.003%

    No Known Activations