© 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. 23-RESID-POST-AA
    11. 5867
    Prev
    Next
    INDEX
    Explanations

    Unity colliders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Repair
    -0.09
    YSTEM
    -0.08
     Stamford
    -0.08
     systemic
    -0.08
    årt
    -0.08
    system
    -0.08
     عباد
    -0.08
    acement
    -0.08
     Pasadena
    -0.08
    (system
    -0.08
    POSITIVE LOGITS
     Rigidbody
    0.15
     capsule
    0.15
     Box
    0.15
     Capsule
    0.15
     collider
    0.13
    Box
    0.13
     Collider
    0.12
    Collider
    0.12
    Caps
    0.12
    (Box
    0.12
    Activations Density 0.006%

    No Known Activations