© 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. 23-RESID-POST-AA
    11. 48454
    Prev
    Next
    INDEX
    Explanations

    anger

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parach
    -0.08
     Spons
    -0.08
     Hitch
    -0.07
     Bayesian
    -0.07
     保存
    -0.07
    与你同行
    -0.07
    募集
    -0.07
    种彩票
    -0.07
     safest
    -0.07
     vrijwill
    -0.07
    POSITIVE LOGITS
     anger
    0.32
     angry
    0.31
     colère
    0.31
    怒
    0.28
     frustration
    0.27
     fury
    0.26
     pissed
    0.26
     раздраж
    0.25
     irritated
    0.25
     annoyed
    0.25
    Activations Density 0.144%

    No Known Activations