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. 112788
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ations
    -0.08
     tahu
    -0.08
    ivere
    -0.08
    -0.07
    ungan
    -0.07
     sle
    -0.07
    ives
    -0.07
     Reel
    -0.07
    ivet
    -0.07
    }else
    -0.07
    POSITIVE LOGITS
     ESA
    0.08
     mesurer
    0.08
     Große
    0.08
     awakening
    0.08
     quedado
    0.08
     jäi
    0.07
     consumidores
    0.07
     ausführ
    0.07
     размеры
    0.07
     Awak
    0.07
    Activations Density 0.014%

    No Known Activations