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. 43404
    Prev
    Next
    INDEX
    Explanations

    Rephrasing or defining concepts

    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
    พบ
    -0.08
    Wnd
    -0.07
    ొన్నారు
    -0.07
    Counters
    -0.07
     encontró
    -0.07
     sept
    -0.07
     theoretically
    -0.07
     triggering
    -0.07
     URLWith
    -0.07
    ولې
    -0.07
    POSITIVE LOGITS
    就是说
    0.16
    つまり
    0.14
    来说
    0.12
     പറഞ്ഞ
    0.11
    而言
    0.11
     nutshell
    0.11
     говоря
    0.11
     essence
    0.10
     decir
    0.10
    �
    0.10
    Activations Density 0.032%

    No Known Activations