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. 53054
    Prev
    Next
    INDEX
    Explanations

    financial gain

    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
     Bubble
    -0.08
     Screen
    -0.07
     Neuro
    -0.07
     off
    -0.07
     bubble
    -0.07
     Countdown
    -0.07
     accesses
    -0.07
     Health
    -0.07
     Clock
    -0.07
     Back
    -0.07
    POSITIVE LOGITS
    赚
    0.10
     продаж
    0.10
    Selling
    0.10
     فروش
    0.09
     লাভ
    0.09
    妹
    0.09
     אח
    0.09
    stag
    0.09
     חי
    0.09
     erzielt
    0.09
    Activations Density 0.021%

    No Known Activations