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. 30646
    Prev
    Next
    INDEX
    Explanations

    on

    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
     silenc
    -0.09
    krieg
    -0.08
    ("$.
    -0.08
     polít
    -0.08
    hop
    -0.08
     Modell
    -0.08
     skyrock
    -0.08
     Möbel
    -0.08
     Frankreich
    -0.07
     Frankrijk
    -0.07
    POSITIVE LOGITS
     、
    0.07
    BW
    0.07
     వె
    0.07
     antar
    0.07
    0.07
     podendo
    0.07
    -vis
    0.07
    	bw
    0.07
     thereof
    0.07
    ्ट्रेल
    0.07
    Activations Density 0.030%

    No Known Activations