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. 76066
    Prev
    Next
    INDEX
    Explanations

    bamboo fabric

    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
     Enc
    -0.10
     subordinate
    -0.08
     WR
    -0.08
     enc
    -0.08
    _enc
    -0.08
     tailoring
    -0.07
     announced
    -0.07
     deliber
    -0.07
    ator
    -0.07
    	SET
    -0.07
    POSITIVE LOGITS
     aloe
    0.10
     טבע
    0.09
     eucalyptus
    0.09
     natürliche
    0.09
    自然
    0.09
     loung
    0.09
     naturelle
    0.09
     자연
    0.09
     Ayurveda
    0.08
     الطبيعي
    0.08
    Activations Density 0.006%

    No Known Activations