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. 60461
    Prev
    Next
    INDEX
    Explanations

    steps and techniques

    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
     touring
    -0.08
     automotive
    -0.08
    nick
    -0.08
    网易
    -0.07
    Nick
    -0.07
    中古
    -0.07
    ециал
    -0.07
     exhibition
    -0.07
    Mal
    -0.07
    装备
    -0.07
    POSITIVE LOGITS
     tensión
    0.08
     length
    0.08
     medit
    0.08
     Spannung
    0.08
     Length
    0.08
    Length
    0.08
     նախագ
    0.08
     gwamn
    0.08
     clamps
    0.08
     సంక
    0.08
    Activations Density 0.007%

    No Known Activations