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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58830
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .ve
    -0.08
    .b
    -0.08
    .facebook
    -0.08
     Vivo
    -0.07
     doute
    -0.07
    .qq
    -0.07
    .mail
    -0.07
     friendly
    -0.07
    _signal
    -0.07
    .a
    -0.07
    POSITIVE LOGITS
     იქნ
    0.10
    以下简称
    0.10
     herein
    0.09
    „
    0.09
     იქნება
    0.09
    არაკ
    0.09
     ہزار
    0.09
    არში
    0.09
    ratulations
    0.08
    რად
    0.08
    Activations Density 0.003%

    No Known Activations