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. 119154
    Prev
    Next
    INDEX
    Explanations

    jump

    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
    人人
    -0.09
    Cust
    -0.08
     increasingly
    -0.08
    .nio
    -0.08
    Buf
    -0.07
    inik
    -0.07
    olos
    -0.07
    -0.07
    Mix
    -0.07
     Geral
    -0.07
    POSITIVE LOGITS
     jumps
    0.11
     discontinu
    0.10
     jump
    0.10
    jump
    0.10
     jumped
    0.09
     несов
    0.09
     abrupt
    0.09
     произош
    0.08
     leaps
    0.08
     رفع
    0.08
    Activations Density 0.006%

    No Known Activations