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. 119168
    Prev
    Next
    INDEX
    Explanations

    Ruined city

    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
     측
    -0.08
     방법
    -0.07
     관리
    -0.07
    ونکی
    -0.07
     Lorsque
    -0.07
     Actualmente
    -0.07
     negoci
    -0.07
     независ
    -0.07
     아�
    -0.07
     nt
    -0.07
    POSITIVE LOGITS
     gennaio
    0.08
     Manila
    0.08
     sociedad
    0.08
     settembre
    0.08
    世纪
    0.07
     vanhu
    0.07
     velja
    0.07
    اضي
    0.07
    城市
    0.07
    旧
    0.07
    Activations Density 0.014%

    No Known Activations