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. 43375
    Prev
    Next
    INDEX
    Explanations

    guarantees

    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
    chts
    -0.09
    kii
    -0.08
     malin
    -0.08
    cht
    -0.08
     Zel
    -0.08
    olid
    -0.08
     criticised
    -0.07
     Lithuania
    -0.07
     Critics
    -0.07
    awy
    -0.07
    POSITIVE LOGITS
     guaranteed
    0.13
     Guaranteed
    0.12
    Guaranteed
    0.12
     assured
    0.12
     assumption
    0.12
     guarantee
    0.10
     assumptions
    0.10
    Guarante
    0.09
     garantiert
    0.09
     предп
    0.09
    Activations Density 0.024%

    No Known Activations