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. 42125
    Prev
    Next
    INDEX
    Explanations

    pot

    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
     Invitation
    -0.09
    >xpath
    -0.08
    Invitation
    -0.08
     mpya
    -0.08
    asc
    -0.08
    жу
    -0.08
     redund
    -0.08
     quelcon
    -0.08
     dambe
    -0.08
     étrange
    -0.08
    POSITIVE LOGITS
     cabinet
    0.09
     indoors
    0.09
     graft
    0.09
    太阳
    0.09
     regimen
    0.08
     Cabinet
    0.08
     warmer
    0.08
     indoor
    0.08
    regel
    0.08
     sıcak
    0.08
    Activations Density 0.012%

    No Known Activations