© 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. 11-RESID-POST-AA
    11. 30909
    Prev
    Next
    INDEX
    Explanations

    Revenge

    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
     fg
    -0.08
     FR
    -0.08
    zimmer
    -0.08
    nect
    -0.08
    ై
    -0.07
     horizons
    -0.07
    ెక్టర్
    -0.07
    /font
    -0.07
     Horizon
    -0.07
     모집
    -0.07
    POSITIVE LOGITS
     revenge
    0.13
     retali
    0.13
     vengeance
    0.13
     retaliation
    0.13
     wrath
    0.12
     veng
    0.12
     न्याय
    0.11
     justicia
    0.11
     ನ್ಯಾಯ
    0.11
     justiça
    0.11
    Activations Density 0.018%

    No Known Activations