© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97312
    Prev
    Next
    INDEX
    Explanations

    Dutch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    开展
    -0.08
    idt
    -0.08
    在线试听
    -0.08
     colaborar
    -0.07
    Página
    -0.07
    上
    -0.07
    PAC
    -0.07
     перейти
    -0.07
    ्ने
    -0.07
    dynt
    -0.07
    POSITIVE LOGITS
    -style
    0.17
    _style
    0.16
     Style
    0.16
    Style
    0.16
     style
    0.15
    	style
    0.15
     стиле
    0.14
    style
    0.14
    _STYLE
    0.14
     शैली
    0.13
    Activations Density 0.046%

    No Known Activations