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. 61296
    Prev
    Next
    INDEX
    Explanations

    Velocity

    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
     sérieux
    -0.09
     overse
    -0.08
    严
    -0.08
     AAA
    -0.08
     fiscal
    -0.07
    琳
    -0.07
     clique
    -0.07
     вк
    -0.07
     monuments
    -0.07
     offic
    -0.07
    POSITIVE LOGITS
     velocity
    0.17
     velocities
    0.16
    _velocity
    0.16
     Geschwindigkeit
    0.15
     velocidades
    0.15
     velocidade
    0.15
    Velocity
    0.15
     Velocity
    0.14
    .velocity
    0.14
     velocidad
    0.14
    Activations Density 0.028%

    No Known Activations