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. 111669
    Prev
    Next
    INDEX
    Explanations

    memory lifetime management

    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
    점을
    -0.08
     confess
    -0.08
     valent
    -0.08
     Play
    -0.08
     Points
    -0.07
     présenté
    -0.07
     Roles
    -0.07
     clinics
    -0.07
     exhibiting
    -0.07
     Productivity
    -0.07
    POSITIVE LOGITS
     pärast
    0.10
     durée
    0.10
    CString
    0.09
     afterwards
    0.09
     afterward
    0.09
     zolang
    0.08
    Later
    0.08
    <void
    0.08
    <data
    0.08
    Reference
    0.08
    Activations Density 0.004%

    No Known Activations