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. 98058
    Prev
    Next
    INDEX
    Explanations

    cybersecurity incidents

    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
    થમ
    -0.09
     taxonomy
    -0.08
    _CHANNEL
    -0.07
     veranderen
    -0.07
     kunnen
    -0.07
    _ASC
    -0.07
     चैन
    -0.07
    ন্ত্রণ
    -0.07
    _UUID
    -0.07
     podrían
    -0.07
    POSITIVE LOGITS
    cito
    0.08
    alad
    0.08
    oleto
    0.08
    -class
    0.08
    сте
    0.08
    &period
    0.08
    755
    0.08
    io
    0.07
     stared
    0.07
    olit
    0.07
    Activations Density 0.000%

    No Known Activations