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. 11-RESID-POST-AA
    6. 106234
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Cisco
    -0.08
     distracting
    -0.08
     vpn
    -0.08
     cresc
    -0.08
     Execute
    -0.08
     SVN
    -0.08
    ssh
    -0.08
     ssh
    -0.08
     -*-
    -0.07
     Sitzung
    -0.07
    POSITIVE LOGITS
     allerg
    0.13
     ASTM
    0.12
    aculture
    0.11
     lactose
    0.11
     эколог
    0.11
     вироб
    0.10
     breeders
    0.10
     fermentation
    0.10
     санитар
    0.10
     производства
    0.10
    Activations Density 0.037%

    No Known Activations