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. 11-RESID-POST-AA
    6. 53960
    Prev
    Next
    INDEX
    Explanations

    cos

    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
     sixteen
    -0.08
     musicale
    -0.08
     matchmaking
    -0.08
     backgrounds
    -0.07
     agg
    -0.07
     länge
    -0.07
    న్న
    -0.07
     abb
    -0.07
    @get
    -0.07
     accl
    -0.07
    POSITIVE LOGITS
     மண
    0.09
    eito
    0.08
     menang
    0.08
     مض
    0.08
    edido
    0.08
     со
    0.07
    tesis
    0.07
     ճ
    0.07
    .SEVERE
    0.07
    泥
    0.07
    Activations Density 0.005%

    No Known Activations