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. 49176
    Prev
    Next
    INDEX
    Explanations

    0

    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
    ावट
    -0.08
    cats
    -0.08
    �
    -0.08
     sacr
    -0.07
    _adv
    -0.07
    _close
    -0.07
    hoes
    -0.07
    vete
    -0.07
    -0.07
    _ab
    -0.07
    POSITIVE LOGITS
     opat
    0.08
    まだ
    0.07
    (ok
    0.07
    まと
    0.07
     doporu
    0.07
     coz
    0.07
    の場合
    0.07
     sensitivity
    0.07
    ETIME
    0.07
    建
    0.07
    Activations Density 0.027%

    No Known Activations