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. 15-RESID-POST-AA
    6. 19090
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     habar
    -0.09
    Dur
    -0.08
     bida
    -0.07
     dement
    -0.07
     chied
    -0.07
     dure
    -0.07
     incorrectly
    -0.07
    ങ്ങി
    -0.07
     dur
    -0.07
     durer
    -0.07
    POSITIVE LOGITS
     Destructor
    0.08
    #else
    0.08
    enciales
    0.08
    retched
    0.07
     சிற
    0.07
    anki
    0.07
     تغيير
    0.07
     Constructor
    0.07
                                                             
    0.07
                                          
    0.07
    Activations Density 0.002%

    No Known Activations