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. 403
    Prev
    Next
    INDEX
    Explanations

    Speed reading

    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
     Helm
    -0.08
    reef
    -0.07
     \
    -0.07
    _PRINTF
    -0.07
    ха
    -0.07
     frag
    -0.07
     обратиться
    -0.07
     Delft
    -0.07
     multa
    -0.07
     fic
    -0.07
    POSITIVE LOGITS
     скорости
    0.11
     velocidad
    0.11
     Speed
    0.11
     vitesse
    0.11
    -Speed
    0.11
     speed
    0.11
     скорость
    0.11
    -paced
    0.11
     snelheid
    0.11
    Speed
    0.11
    Activations Density 0.008%

    No Known Activations