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. 27175
    Prev
    Next
    INDEX
    Explanations

    192

    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
     Tc
    -0.08
     विश्व
    -0.08
     resurf
    -0.07
    yel
    -0.07
     वार
    -0.07
    ลง
    -0.07
    indic
    -0.07
     sprung
    -0.07
    בה
    -0.07
    resses
    -0.07
    POSITIVE LOGITS
     Scott
    0.09
     Díaz
    0.08
     Friedman
    0.08
    �
    0.08
     Unt
    0.07
     boys
    0.07
     tuned
    0.07
     Diaz
    0.07
    -o
    0.07
    屏
    0.07
    Activations Density 0.016%

    No Known Activations