Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49162
    Prev
    Next
    INDEX
    Explanations

    Speed and 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
     blem
    -0.08
     강조
    -0.08
     exigir
    -0.08
     fiscal
    -0.08
     기간
    -0.08
     matemática
    -0.07
     보는
    -0.07
    .er
    -0.07
     demanda
    -0.07
    .require
    -0.07
    POSITIVE LOGITS
     गति
    0.12
    -speed
    0.12
     speeds
    0.12
    _speed
    0.12
    _SPEED
    0.12
    速度
    0.11
    Speed
    0.11
     velocities
    0.10
     snelheid
    0.10
     حركة
    0.10
    Activations Density 0.033%

    No Known Activations