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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98191
    Prev
    Next
    INDEX
    Explanations

    �

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ეწ
    -0.10
    	br
    -0.10
    Engine
    -0.09
    .engine
    -0.09
    	engine
    -0.09
    ikeza
    -0.09
     Engine
    -0.09
    ირთ
    -0.09
    .Engine
    -0.09
    >equals
    -0.09
    POSITIVE LOGITS
    �
    0.13
    �
    0.10
     TXT
    0.08
    k
    0.08
    �
    0.07
    �
    0.07
    _k
    0.07
    *
    0.07
     UDP
    0.07
     LGBTQ
    0.07
    Activations Density 0.001%

    No Known Activations