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. 77307
    Prev
    Next
    INDEX
    Explanations

    LCM calculations

    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
     übers
    -0.09
     Bratis
    -0.08
     offsets
    -0.08
    اءات
    -0.08
     muitos
    -0.08
    _offsets
    -0.07
    증
    -0.07
     vare
    -0.07
    Offsets
    -0.07
     nọmba
    -0.07
    POSITIVE LOGITS
    Latest
    0.10
    angezien
    0.09
    .union
    0.08
    .content
    0.08
     WOM
    0.08
     হল
    0.08
     최신
    0.08
     સમાવેશ
    0.08
     പഴ
    0.08
    latest
    0.08
    Activations Density 0.013%

    No Known Activations