© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102966
    Prev
    Next
    INDEX
    Explanations

    Actions and verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    พู
    -0.08
     we'd
    -0.08
     we
    -0.08
     so
    -0.08
     emisiones
    -0.07
    ró
    -0.07
    odz
    -0.07
    so
    -0.07
     આપણે
    -0.07
    ūros
    -0.07
    POSITIVE LOGITS
    ிக்கை
    0.08
     stessa
    0.08
    олага
    0.08
    ियर
    0.08
     pouze
    0.08
    @No
    0.08
    िकेट
    0.08
     questo
    0.08
    त्ति
    0.08
     certaines
    0.08
    Activations Density 0.339%

    No Known Activations