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. 8379
    Prev
    Next
    INDEX
    Explanations

    yellow

    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
    أ
    -0.07
     Fü
    -0.07
     menc
    -0.07
    ERT
    -0.07
    Trans
    -0.07
     mètres
    -0.07
    यों
    -0.07
    ฝ
    -0.07
     certa
    -0.06
    hos
    -0.06
    POSITIVE LOGITS
     Corey
    0.09
    �
    0.09
    -orang
    0.09
    -eyed
    0.08
     sludge
    0.08
    -orange
    0.08
    色综合
    0.08
     اللون
    0.08
     cracker
    0.08
    -green
    0.08
    Activations Density 0.009%

    No Known Activations