© 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. 11-RESID-POST-AA
    11. 111027
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Map
    -0.08
    .Profile
    -0.08
     Mme
    -0.07
    isal
    -0.07
     benefici
    -0.07
     fortalecer
    -0.07
     ocorrência
    -0.07
     감사합니다
    -0.07
    搏
    -0.07
    Kd
    -0.07
    POSITIVE LOGITS
     horribly
    0.11
     terribly
    0.10
     terrible
    0.09
     horrible
    0.09
     sprawling
    0.09
     awful
    0.09
     whatsoever
    0.08
     atroc
    0.08
     curse
    0.08
     notoriously
    0.08
    Activations Density 0.050%

    No Known Activations