© 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. 78501
    Prev
    Next
    INDEX
    Explanations

    self-compassion

    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
    igos
    -0.08
     Encourage
    -0.08
     Fashion
    -0.07
     dissect
    -0.07
     fad
    -0.07
     Feeling
    -0.07
     شع
    -0.07
     malo
    -0.07
    aktion
    -0.07
     तौर
    -0.07
    POSITIVE LOGITS
    ്ര
    0.08
     LTC
    0.08
    ယ
    0.08
     cq
    0.08
    രാജ
    0.08
     cn
    0.08
    stvo
    0.08
    দেশ
    0.07
    اما
    0.07
    ourced
    0.07
    Activations Density 0.003%

    No Known Activations