Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106117
    Prev
    Next
    INDEX
    Explanations

    sort

    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
     geef
    -0.09
     пенсион
    -0.08
     blijf
    -0.07
    扶贫
    -0.07
    扎
    -0.07
    getter
    -0.07
     tidy
    -0.07
     경제
    -0.07
     unten
    -0.07
    kon
    -0.07
    POSITIVE LOGITS
     byt
    0.07
    OMET
    0.07
     appointment
    0.07
     packing
    0.07
     لما
    0.07
     focus
    0.07
     Actualmente
    0.07
     natu
    0.07
     shrug
    0.07
     uphill
    0.07
    Activations Density 0.000%

    No Known Activations