© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129378
    Prev
    Next
    INDEX
    Explanations

    formatting/emphasis characters

    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
     DVB
    -0.08
     ಬರುತ್ತ
    -0.07
    .vert
    -0.07
     disproportion
    -0.07
     मामले
    -0.07
    -0.07
     readable
    -0.07
     Manufactured
    -0.07
     \(
    -0.07
    ciu
    -0.07
    POSITIVE LOGITS
     mindfulness
    0.14
     hobbies
    0.13
     gratitude
    0.12
     mentorship
    0.11
     forgiveness
    0.11
     meditation
    0.11
     solitude
    0.11
     savor
    0.11
     cherish
    0.10
     Passion
    0.10
    Activations Density 0.019%

    No Known Activations