© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 815
    Prev
    Next
    INDEX
    Explanations

    [MAX

    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
     SHORT
    -0.09
     Short
    -0.08
    sense
    -0.08
    ITT
    -0.08
    Vip
    -0.07
    .Short
    -0.07
     flowed
    -0.07
     relocated
    -0.07
     psychic
    -0.07
     korte
    -0.07
    POSITIVE LOGITS
     regression
    0.09
    	N
    0.08
     Cer
    0.08
     knot
    0.08
    	c
    0.07
     overshadow
    0.07
    _reg
    0.07
     cabbage
    0.07
     tape
    0.07
    -worthy
    0.07
    Activations Density 0.001%

    No Known Activations