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. 53277
    Prev
    Next
    INDEX
    Explanations

    -on

    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
     ggf
    -0.09
    Balls
    -0.09
     inert
    -0.08
     cheaply
    -0.08
     cheap
    -0.08
     corpse
    -0.08
     Dhe
    -0.07
    lip
    -0.07
    ???↵
    -0.07
    -0.07
    POSITIVE LOGITS
     meticulously
    0.12
     тщательно
    0.10
     tirelessly
    0.10
     undoubtedly
    0.10
     внимательно
    0.10
     ведь
    0.09
     firsthand
    0.09
     thoughtfully
    0.09
     diligently
    0.09
     vores
    0.09
    Activations Density 0.199%

    No Known Activations