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. 15-RESID-POST-AA
    6. 18957
    Prev
    Next
    INDEX
    Explanations

    Restricted movement area

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elt
    -0.08
     linen
    -0.07
    会议
    -0.07
     appetizer
    -0.07
     losers
    -0.07
    _epoch
    -0.07
    (number
    -0.07
          
    -0.07
     العدد
    -0.07
     tand
    -0.07
    POSITIVE LOGITS
    限制
    0.13
     unrestricted
    0.12
     সীম
    0.12
    Restricted
    0.12
     reachable
    0.12
     unlimited
    0.11
     restricted
    0.11
     제한
    0.11
    limited
    0.11
     Restricted
    0.11
    Activations Density 0.006%

    No Known Activations