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. 54160
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and annotations

    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
     uitstraling
    -0.09
     behaving
    -0.08
     istället
    -0.08
     جيڪو
    -0.08
     jackpot
    -0.07
     behaved
    -0.07
    -0.07
     결
    -0.07
    راعة
    -0.07
     žal
    -0.07
    POSITIVE LOGITS
     предполага
    0.10
     hypothetical
    0.10
     rough
    0.10
     assumes
    0.10
     bedoeld
    0.09
     preliminary
    0.09
     illustrative
    0.09
     slechts
    0.09
     abstra
    0.09
     مجرد
    0.09
    Activations Density 0.026%

    No Known Activations