Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77393
    Prev
    Next
    INDEX
    Explanations

    memory allocation

    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
     робот
    -0.09
     Surveillance
    -0.09
     patent
    -0.08
     Patent
    -0.08
    Qualifications
    -0.08
     roda
    -0.07
    變
    -0.07
    Skills
    -0.07
     confidentiality
    -0.07
    $/,
    -0.07
    POSITIVE LOGITS
    (sizeof
    0.11
    .alloc
    0.10
     malloc
    0.10
     allocation
    0.09
     Allocate
    0.09
    malloc
    0.09
     allocating
    0.09
    .allocate
    0.08
     Alloc
    0.08
    (size
    0.08
    Activations Density 0.005%

    No Known Activations