© 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. 11-RESID-POST-AA
    11. 26176
    Prev
    Next
    INDEX
    Explanations

    martial arts kicking

    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
     underwriting
    -0.08
     Alba
    -0.08
     Iceland
    -0.08
     “
    -0.07
     Jira
    -0.07
     Mend
    -0.07
     тик
    -0.07
     Customize
    -0.07
     Arc
    -0.07
     North
    -0.07
    POSITIVE LOGITS
     دفاع
    0.09
     poderosa
    0.09
     unreachable
    0.08
    'ল
    0.08
    .te
    0.08
    ตู
    0.08
    угу
    0.08
    -क
    0.08
    Threat
    0.08
    .attack
    0.08
    Activations Density 0.004%

    No Known Activations