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. 12243
    Prev
    Next
    INDEX
    Explanations

    Seasons

    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
     이번
    -0.08
     ayer
    -0.08
     вчера
    -0.08
     gisteren
    -0.08
     headline
    -0.08
     сегодня
    -0.08
    -knit
    -0.08
    ข่าว
    -0.07
    vida
    -0.07
     bisher
    -0.07
    POSITIVE LOGITS
     ובע
    0.08
    期间
    0.08
    頃
    0.08
    ிலும்
    0.08
    .FILL
    0.08
     favoriser
    0.08
    様
    0.07
    .grad
    0.07
    �
    0.07
    尤其
    0.07
    Activations Density 0.036%

    No Known Activations