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. 58292
    Prev
    Next
    INDEX
    Explanations

    underworld mythologies

    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
     Buffered
    -0.09
     షూట
    -0.09
    	Buffered
    -0.08
     ગણ
    -0.08
    Buffered
    -0.08
     puedas
    -0.08
    .Width
    -0.08
     ફોટ
    -0.08
     probi
    -0.08
    .Buffered
    -0.08
    POSITIVE LOGITS
     subterr
    0.10
     underground
    0.10
    地下
    0.09
     anba
    0.09
     bawah
    0.09
     beneath
    0.09
     கீழ
    0.09
    二区
    0.08
     vicious
    0.08
     categorias
    0.08
    Activations Density 0.014%

    No Known Activations