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. 15-RESID-POST-AA
    6. 18994
    Prev
    Next
    INDEX
    Explanations

    #

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.08
     VE
    -0.08
     That
    -0.08
     SOME
    -0.07
     that
    -0.07
     Ve
    -0.07
     IST
    -0.07
     nons
    -0.07
    ?”↵↵
    -0.07
     something
    -0.07
    POSITIVE LOGITS
    ტ
    0.09
    commercial
    0.09
     туру
    0.09
    Twitter
    0.09
    Wikipedia
    0.09
    named
    0.09
    โพ
    0.09
     aansluiten
    0.09
    “
    0.08
    nombre
    0.08
    Activations Density 0.025%

    No Known Activations