Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12162
    Prev
    Next
    INDEX
    Explanations

    self destruct

    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
     heading
    -0.08
    ihat
    -0.08
    ��
    -0.08
     `,↵
    -0.07
     climbing
    -0.07
     Heading
    -0.07
    Heading
    -0.07
     estava
    -0.07
     inequalities
    -0.07
     spel
    -0.07
    POSITIVE LOGITS
    (delete
    0.15
     уничтож
    0.15
    删除
    0.15
     destruir
    0.15
     destroy
    0.14
     Destroy
    0.14
    destroy
    0.14
     löschen
    0.14
    Delete
    0.14
     destroys
    0.14
    Activations Density 0.040%

    No Known Activations