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. 77810
    Prev
    Next
    INDEX
    Explanations

    reward conditioning

    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
     filenames
    -0.08
     populate
    -0.08
     Compute
    -0.08
    Fal
    -0.08
     abra
    -0.08
     Populate
    -0.08
     manta
    -0.08
     nač
    -0.08
     profess
    -0.08
    OSS
    -0.07
    POSITIVE LOGITS
    奖励
    0.15
    .reward
    0.14
     reward
    0.14
     rewards
    0.14
    _reward
    0.14
     recompensa
    0.13
     Reward
    0.13
     rewarding
    0.13
    Reward
    0.13
     rewarded
    0.13
    Activations Density 0.014%

    No Known Activations