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. 65780
    Prev
    Next
    INDEX
    Explanations

    want

    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
     balloon
    -0.08
     zastos
    -0.08
     примен
    -0.08
    bericht
    -0.08
    �
    -0.07
    rlə
    -0.07
     varð
    -0.07
    сен
    -0.07
     bulbs
    -0.07
    ges
    -0.07
    POSITIVE LOGITS
     ಬಾರಿ
    0.09
    ",(
    0.08
     nötig
    0.08
     contiguous
    0.07
     asociaciones
    0.07
     limitado
    0.07
     diperlukan
    0.07
     तक
    0.07
     calcul
    0.07
     פעמים
    0.07
    Activations Density 0.007%

    No Known Activations