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. 7-RESID-POST-AA
    6. 2001
    Prev
    Next
    INDEX
    Explanations

    Triple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wf
    -0.07
     deten
    -0.07
     hump
    -0.07
     incarnation
    -0.07
     SATA
    -0.07
     behold
    -0.07
    wadi
    -0.07
     Woj
    -0.07
     pec
    -0.07
    alary
    -0.07
    POSITIVE LOGITS
     государственного
    0.07
    669
    0.07
     rap
    0.07
     negatives
    0.07
     contrad
    0.07
     singles
    0.07
    Neg
    0.07
    یدی
    0.06
     foe
    0.06
    (sequence
    0.06
    Activations Density 0.008%

    No Known Activations