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. 12018
    Prev
    Next
    INDEX
    Explanations

    1

    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
    /manage
    -0.08
    /address
    -0.08
     charts
    -0.08
     TIM
    -0.08
     Invest
    -0.07
    soe
    -0.07
    עות
    -0.07
    .Num
    -0.07
     Has
    -0.07
     sustainably
    -0.07
    POSITIVE LOGITS
     ellipse
    0.10
    ellipsis
    0.09
     penalties
    0.08
    _BINARY
    0.08
     knife
    0.08
     kth
    0.08
    .binary
    0.08
    atha
    0.08
    ixi
    0.08
     ell
    0.08
    Activations Density 0.001%

    No Known Activations