© 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. 97476
    Prev
    Next
    INDEX
    Explanations

    finding maximums

    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
     masterpieces
    -0.09
     махсус
    -0.09
     mawr
    -0.09
    වර
    -0.08
    ließlich
    -0.08
    ovací
    -0.08
     içine
    -0.08
     maksimal
    -0.08
    ların
    -0.08
     jeweils
    -0.08
    POSITIVE LOGITS
     achievable
    0.26
     attainable
    0.24
     attained
    0.21
     achieved
    0.21
     possible
    0.21
     among
    0.20
     possível
    0.19
     posible
    0.19
     occurs
    0.19
    _possible
    0.18
    Activations Density 0.133%

    No Known Activations