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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11664
    Prev
    Next
    INDEX
    Explanations

    language possessives/grammar

    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
     отправ
    -0.09
    .restart
    -0.08
     reboot
    -0.08
    �
    -0.08
     restarting
    -0.08
    (JSON
    -0.08
    Restart
    -0.08
    _enqueue
    -0.08
    (xhr
    -0.08
    _restart
    -0.07
    POSITIVE LOGITS
    ownership
    0.12
     ownership
    0.12
     Ownership
    0.11
    Ownership
    0.11
     owned
    0.11
     માલ
    0.10
     مالک
    0.10
     ബന്ധ
    0.10
    _OWNER
    0.10
     Besitz
    0.10
    Activations Density 0.016%

    No Known Activations