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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79164
    Prev
    Next
    INDEX
    Explanations

    gossip and rumors

    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
    @author
    -0.08
    rechte
    -0.08
     direitos
    -0.08
     plong
    -0.08
     author's
    -0.07
    ramento
    -0.07
     защиты
    -0.07
     добро
    -0.07
     pose
    -0.07
    ificación
    -0.07
    POSITIVE LOGITS
     gossip
    0.19
     rumors
    0.17
     whispers
    0.15
     rumores
    0.15
     whispered
    0.14
     rumor
    0.14
     rumours
    0.14
     Gossip
    0.13
     слух
    0.12
     bouche
    0.11
    Activations Density 0.048%

    No Known Activations