Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53220
    Prev
    Next
    INDEX
    Explanations

    currency

    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
    برى
    -0.08
     sovereign
    -0.08
     prejud
    -0.07
     alo
    -0.07
     sovereignty
    -0.07
    präg
    -0.07
     political
    -0.07
     justicia
    -0.07
     souver
    -0.07
     nhau
    -0.07
    POSITIVE LOGITS
     contrasted
    0.07
     mesh
    0.07
    rottle
    0.07
    ithe
    0.07
    SUM
    0.07
    mart
    0.07
    (mean
    0.07
     புத
    0.07
    OSE
    0.07
    egel
    0.07
    Activations Density 0.002%

    No Known Activations