© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64057
    Prev
    Next
    INDEX
    Explanations

    bomb

    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
    champ
    -0.07
    (on
    -0.07
     lateral
    -0.07
     BASIC
    -0.07
     broth
    -0.07
     ascent
    -0.07
    握
    -0.07
     Scrap
    -0.07
    XS
    -0.07
     ומת
    -0.07
    POSITIVE LOGITS
     bombing
    0.11
     campaigns
    0.10
     raids
    0.10
     bombard
    0.10
     targeting
    0.09
     targeted
    0.09
     камп
    0.09
     campaign
    0.09
     campagnes
    0.09
     cibl
    0.08
    Activations Density 0.019%

    No Known Activations