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. 15-RESID-POST-AA
    6. 19309
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .chain
    -0.08
     পানি
    -0.08
     Creator
    -0.08
     Types
    -0.07
     Exception
    -0.07
    _types
    -0.07
    infection
    -0.07
     Chain
    -0.07
    ypy
    -0.07
    .r
    -0.07
    POSITIVE LOGITS
    ('@/
    0.09
     стоят
    0.09
     зориул
    0.09
     арналған
    0.08
     али
    0.08
    თვის
    0.08
     могуць
    0.08
     geef
    0.08
     anmeld
    0.08
    gebracht
    0.08
    Activations Density 0.001%

    No Known Activations