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. 11-RESID-POST-AA
    6. 53974
    Prev
    Next
    INDEX
    Explanations

    names

    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
    	stack
    -0.09
     설정
    -0.08
     सब
    -0.08
     ::=
    -0.07
     PCI
    -0.07
    ceptor
    -0.07
     स
    -0.07
    ())↵
    -0.07
     સ
    -0.07
     hoàn
    -0.07
    POSITIVE LOGITS
     nickname
    0.14
    昵称
    0.13
    nickname
    0.13
    Nickname
    0.12
    aliases
    0.11
     abbrevi
    0.11
     shorthand
    0.11
     aliases
    0.11
     nick
    0.11
     abbreviation
    0.10
    Activations Density 0.067%

    No Known Activations