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. 15-RESID-POST-AA
    6. 19544
    Prev
    Next
    INDEX
    Explanations

    "in" (foreign languages)

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|reserved_200004|>
    -0.08
     사랑
    -0.08
    atrics
    -0.08
     erlebt
    -0.08
     және
    -0.07
    .No
    -0.07
     experiências
    -0.07
     люблю
    -0.07
    ଶ
    -0.07
     punish
    -0.07
    POSITIVE LOGITS
    里面
    0.12
     ensuing
    0.09
     newfound
    0.09
     συνέχεια
    0.09
     Allí
    0.08
    过程中
    0.08
     newly
    0.08
    其中
    0.08
     gouf
    0.08
    �
    0.08
    Activations Density 0.007%

    No Known Activations