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. 90207
    Prev
    Next
    INDEX
    Explanations

    nothing but

    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
    چې
    -0.08
    )+"
    -0.07
    ausal
    -0.07
    پ
    -0.07
    pei
    -0.07
    ioon
    -0.07
     Lagu
    -0.07
     Leh
    -0.07
    pcion
    -0.07
     underv
    -0.07
    POSITIVE LOGITS
    মাত্র
    0.09
     лишь
    0.08
     solace
    0.08
     rubble
    0.08
     bare
    0.08
     POD
    0.08
    ാതെ
    0.08
    .databinding
    0.08
     Tribal
    0.08
     fluff
    0.08
    Activations Density 0.043%

    No Known Activations