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. 112116
    Prev
    Next
    INDEX
    Explanations

    spreadsheet cell references

    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
     설명
    -0.09
     बिल
    -0.08
    由
    -0.08
     Lego
    -0.08
    कार्य
    -0.08
     thrilling
    -0.07
    .One
    -0.07
    	   
    -0.07
    説明
    -0.07
    令人
    -0.07
    POSITIVE LOGITS
     anchored
    0.09
     anchors
    0.09
     tournée
    0.08
     korun
    0.08
     anch
    0.08
    anker
    0.08
    Anch
    0.08
    tdown
    0.08
     CRS
    0.07
     сохраня
    0.07
    Activations Density 0.002%

    No Known Activations