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. 49378
    Prev
    Next
    INDEX
    Explanations

    Calculations and remainders

    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
     attack
    -0.07
     فقد
    -0.07
    �
    -0.07
     zu
    -0.07
     sign
    -0.07
     বাঁ
    -0.07
    /controller
    -0.07
     bre
    -0.07
     quickly
    -0.07
     اللو
    -0.07
    POSITIVE LOGITS
     leftover
    0.14
    Carry
    0.13
     leftovers
    0.11
     Resid
    0.11
    Residual
    0.11
     Carry
    0.10
     residual
    0.10
     carry
    0.10
    carry
    0.10
     reutil
    0.10
    Activations Density 0.010%

    No Known Activations