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. 48984
    Prev
    Next
    INDEX
    Explanations

    cutting and separation

    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
     tuổi
    -0.08
     ellen
    -0.08
     steg
    -0.08
     verwe
    -0.08
     nargin
    -0.08
     leeftijd
    -0.08
     với
    -0.08
     thay
    -0.07
     amad
    -0.07
    晚
    -0.07
    POSITIVE LOGITS
     unfold
    0.11
     unfolding
    0.09
     flatten
    0.09
    展开
    0.09
     unfolded
    0.09
     aberto
    0.08
     unfolds
    0.08
     geöffnet
    0.08
    Breaking
    0.08
     abierto
    0.08
    Activations Density 0.007%

    No Known Activations