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. 76589
    Prev
    Next
    INDEX
    Explanations

    opposed

    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
     moje
    -0.08
    製
    -0.08
     więcej
    -0.07
     Rewrite
    -0.07
    ((((
    -0.07
    �
    -0.07
    開
    -0.07
    粉
    -0.07
    応募
    -0.07
     Ike
    -0.07
    POSITIVE LOGITS
     contrasted
    0.13
     distinction
    0.11
     ozna
    0.11
     distinguished
    0.11
     distinguir
    0.11
     distinguishing
    0.10
     Gegensatz
    0.10
     distinctions
    0.10
     disting
    0.10
     distinguishes
    0.10
    Activations Density 0.072%

    No Known Activations