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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98586
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	dialog
    -0.08
    stig
    -0.08
    equipment
    -0.07
    amine
    -0.07
    -St
    -0.07
    PT
    -0.07
        
    -0.07
     Paid
    -0.07
    ាក
    -0.07
    лиз
    -0.07
    POSITIVE LOGITS
     Castel
    0.08
     waist
    0.08
     Dad
    0.08
     dhin
    0.08
     zith
    0.08
     Ethernet
    0.08
     oranges
    0.08
     combin
    0.08
     thigh
    0.08
     bone
    0.08
    Activations Density 0.003%

    No Known Activations